├── LICENSE ├── README.md ├── create ├── Camera │ └── corruptions.py ├── LiDAR │ ├── cross_sensor │ │ ├── cross_sensor.sh │ │ └── gen_cross_sensor.py │ ├── crosstalk │ │ ├── crosstalk.sh │ │ └── gen_crosstalk.py │ ├── fog │ │ ├── LICENSE │ │ ├── file_lists │ │ │ ├── A2D2.txt │ │ │ ├── Apollo.txt │ │ │ ├── Argoverse.txt │ │ │ ├── DENSE.txt │ │ │ ├── Honda3D.txt │ │ │ ├── LyftL5.txt │ │ │ ├── PandaSet.txt │ │ │ ├── WAYMO.txt │ │ │ └── nuScenes.txt │ │ └── generate_integral_lookup_table.py │ └── motion_blur │ │ ├── gen_motion.py │ │ └── motion_blur.sh └── README.md └── docs ├── GIFs ├── camera │ ├── brightness-easy.gif │ ├── brightness-hard.gif │ ├── brightness-mid.gif │ ├── camera-crash-easy.gif │ ├── camera-crash-hard.gif │ ├── camera-crash-mid.gif │ ├── clean.gif │ ├── color-quant-easy.gif │ ├── color-quant-hard.gif │ ├── color-quant-mid.gif │ ├── fog-easy.gif │ ├── fog-hard.gif │ ├── fog-mid.gif │ ├── frame-lost-easy.gif │ ├── frame-lost-hard.gif │ ├── frame-lost-mid.gif │ ├── low-light-easy.gif │ ├── low-light-hard.gif │ ├── low-light-mid.gif │ ├── motion-blur-easy.gif │ ├── motion-blur-hard.gif │ ├── motion-blur-mid.gif │ ├── snow-easy.gif │ ├── snow-hard.gif │ └── snow-mid.gif └── lidar │ ├── beam_missing-heavy.gif │ ├── beam_missing-light.gif │ ├── beam_missing-moderate.gif │ ├── clean.gif │ ├── cross_sensor-heavy.gif │ ├── cross_sensor-light.gif │ ├── cross_sensor-moderate.gif │ ├── crosstalk-heavy.gif │ ├── crosstalk-light.gif │ ├── crosstalk-moderate.gif │ ├── fog-heavy.gif │ ├── fog-light.gif │ ├── fog-moderate.gif │ ├── incomplete_echo-heavy.gif │ ├── incomplete_echo-light.gif │ ├── incomplete_echo-moderate.gif │ ├── motion_blur-heavy.gif │ ├── motion_blur-light.gif │ ├── motion_blur-moderate.gif │ ├── snow-heavy.gif │ ├── snow-light.gif │ ├── snow-moderate.gif │ ├── wet_ground-heavy.gif │ ├── wet_ground-light.gif │ └── wet_ground-moderate.gif └── images ├── benchmark.png ├── definition.png ├── levels.png ├── logo.png ├── maptr.png ├── metrics_Fusion.png ├── metrics_LiDAR.png ├── metrics_camera.png ├── qua.png ├── robustness.png └── teaser.png /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |

English | 简体中文

2 | 3 | 4 |

5 | 6 | 7 |

Is Your HD Map Constructor Reliable under Sensor Corruptions?

8 | 9 |

10 | Xiaoshuai Hao1    11 | Mengchuan Wei1    12 | Yifan Yang1    13 | Haimei Zhao
14 | Hui Zhang1    15 | Yi Zhou1    16 | Qiang Wang1    17 | Weiming Li
18 | Lingdong Kong3,‡    19 | Jing Zhang2,‡ 20 |

21 | 1Samsung R&D Institute China-Beijing    22 | 2The University of Sydney    23 | 3National University of Singapore 24 |

25 | 26 |

27 | 28 |

29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 |

49 | 50 | 51 | 52 | ## About 53 | `MapBench` is the first comprehensive benchmark designed to evaluate the out-of-domain robustness of HD map construction methods against various sensor corruptions. 54 | 55 | | | 56 | | :-: | 57 | | Our benchmark encompasses a total of 16 corruption types for HD map construction, which can be categorized into exterior, interior, and sensor failure scenarios. Besides, we define 13 multi-sensor corruptions by combining the camera and LiDAR sensor failure types. | 58 | 59 | 60 | 61 | ## Updates 62 | 63 | - \[2024.06\] - Launch of the `MapBench` benchmark. In this version, we include a total of **31** HD map construction models, evaluated on **29** different camera and LiDAR corruption types across **3** severity levels. 64 | 65 | 66 | 67 | ## Outline 68 | 69 | - [Benchmark Definition](#bar_chart-benchmark-definition) 70 | - [Installation](#gear-installation) 71 | - [Data Preparation](#hotsprings-data-preparation) 72 | - [Getting Started](#rocket-getting-started) 73 | - [Model Zoo](#high_brightness-model-zoo) 74 | - [Benchmark](#golf-benchmark) 75 | - [TODO List](#memo-todo-list) 76 | - [Citation](#citation) 77 | - [License](#license) 78 | - [Acknowledgements](#acknowledgements) 79 | 80 | 81 | ## :bar_chart: Benchmark Definition 82 | 83 | `MapBench` consists of a total of **29** different sensor corruption scenarios, including **8** types of camera corruptions, **8** types of LiDAR corruptions, and **13** types of camera-LiDAR corruption combinations. 84 | 85 | 86 | ### LiDAR Sensor Corruptions 87 | 88 | ||||| 89 | | :---: | :---: | :---: | :---: | 90 | | | | | | 91 | | **Wet Ground** | **Snow** | **Beam Missing** | **Incomplete Echo** | 92 | | | | | | 93 | | **Fog** | **Motion Blur** | **Crosstalk** | **Cross-Sensor** | 94 | || 95 | 96 | | Type | Description | Parameter | Easy | Moderate | Hard | 97 | | :-: | :-: | :-: | :-: | :-: | :-: | 98 | | Wet Ground | significantly attenuated laser echoes | (water height, noise floor) | (0.2, 0.2) | (1.0, 0.3) | (1.2, 0.7) | 99 | | Snow | back-scattering and attenuation of LiDAR points | (snowfall rate, terminal velocity) | (0.5, 2.0) | (1.0, 1.6) | (2.5, 1.6) | 100 | | Beam Missing | loss of certain light impulses | beam number to drop | 8 | 16 | 24 | 101 | | Incomplete Echo | incomplete LiDAR readings | drop ratio | 0.75 | 0.85 | 0.95 | 102 | | Fog | back-scattering and attenuation of LiDAR points | beta | 0.008 | 0.05 | 0.2 | 103 | | Motion Blur | blur caused by vehicle movement | trans std | 0.2 | 0.3 | 0.4 | 104 | | Crosstalk | light impulses interference | percentage | 0.03 | 0.07 | 0.12 | 105 | | Cross-Sensor | cross sensor data | beam number to drop | 8 | 16 | 20 | 106 | 107 | 108 | ### Camera Sensor Corruptions 109 | 110 | |||| 111 | | :---: | :---: | :---: | 112 | | | | | 113 | | **Brightness** | **Low-Light** | **Fog** | 114 | | | | | 115 | | **Snow** | **Motion Blur** | **Color Quant** | 116 | || 117 | 118 | | Type | Description | Parameter | Easy | Moderate | Hard | 119 | | :-: | :-: | :-: | :-: | :-: | :-: | 120 | | Brightness | varying daylight intensity | adjustment in HSV space | 0.2 | 0.4 | 0.5 | 121 | | Low-Light | varying daylight intensity | scale factor | 0.5 | 0.4 | 0.3 | 122 | | Fog | a visually obstructive form of precipitation | (thickness, smoothness) | (2.0, 2.0) | (2.5, 1.5) | (3.0, 1.4) | 123 | | Snow | a visually obstructive form of precipitation | (mean, std, scale, threshold, blur radius, blur std, blending ratio) | (0.1, 0.3, 3.0, 0.5, 10.0, 4.0, 0.8) | (0.2, 0.3, 2, 0.5, 12, 4, 0.7) | (0.55, 0.3, 4, 0.9, 12, 8, 0.7) | 124 | | Motion Blur | moving camera quickly | (radius, sigma) | (15, 5) | (15, 12) | (20, 15) | 125 | | Color Quant | reducing the number of colors | bit number | 5 | 4 | 3 | 126 | 127 | 128 | ### Camera Sensor Failures 129 | 130 | ||| 131 | |:-:|:-:| 132 | | | | 133 | | Frame Lost | Camera Crash | 134 | || 135 | 136 | | Type | Description | Parameter | Easy | Moderate | Hard | 137 | | :-: | :-: | :-: | :-: | :-: | :-: | 138 | | Frame Lost | dropping temporal frames | probability of frame dropping | 2/6 | 4/6 | 5/6 | 139 | | Camera Crash | dropping view images | number of dropped cameras | 2 | 4 | 5 | 140 | 141 | 142 | 143 | ## :gear: Installation 144 | 145 | For details related to installation, kindly refer to [INSTALL.md](docs/INSTALL.md). 146 | 147 | 148 | 149 | ## :hotsprings: Data Preparation 150 | 151 | Our datasets are hosted by [OpenDataLab](https://opendatalab.com/). 152 | >
153 | > OpenDataLab is a pioneering open data platform for the large AI model era, making datasets accessible. By using OpenDataLab, researchers can obtain free formatted datasets in various fields. 154 | 155 | Kindly refer to [DATA_PREPARE.md](docs/DATA_PREPARE.md) for the details to prepare the training and evaluation datasets. 156 | 157 | 158 | ## :rocket: Getting Started 159 | 160 | To learn more usage about this codebase, kindly refer to [GET_STARTED.md](docs/GET_STARTED.md). 161 | 162 | 163 | 164 | ## :high_brightness: Model Zoo 165 | 166 |
167 |  HD Map Construction 168 | 169 | > - [x] **[HDMapNet](https://arxiv.org/abs/2107.06307), ICRA 2022.** [**`[Code]`**](https://github.com/Tsinghua-MARS-Lab/HDMapNet) 170 | > - [x] **[VectorMapNet](https://arxiv.org/abs/2206.08920), ICML 2023.** [**`[Code]`**](https://github.com/Mrmoore98/VectorMapNet_code) 171 | > - [x] **[MapTR](https://arxiv.org/abs/2208.14437), ICLR 2023.** [**`[Code]`**](https://github.com/hustvl/MapTR) 172 | > - [x] **[MapTRv2](https://arxiv.org/abs/2308.05736), arXiv 2023.** [**`[Code]`**](https://github.com/hustvl/MapTR) 173 | > - [x] **[PivotNet](https://arxiv.org/pdf/2308.16477), ICCV 2023.** [**`[Code]`**](https://github.com/wenjie710/PivotNet) 174 | > - [x] **[BeMapNet](https://openaccess.thecvf.com/content/CVPR2023/html/Qiao_End-to-End_Vectorized_HD-Map_Construction_With_Piecewise_Bezier_Curve_CVPR_2023_paper.html), CVPR 2023.** [**`[Code]`**](https://github.com/er-muyue/BeMapNet) 175 | > - [x] **[StreamMapNet](https://arxiv.org/abs/2308.12570), WACV 2024.** [**`[Code]`**](https://github.com/yuantianyuan01/StreamMapNet) 176 | > - [x] **[HIMap](https://arxiv.org/abs/2308.12570), CVPR 2024.** [**`[Code]`**]() 177 | 178 |
179 | 180 | 181 | 182 | 183 | ## :golf: Benchmark 184 | 185 | The *mean average precision (mAP)* is consistently used as the main indicator for evaluating model performance in our HD Map construction benchmark. 186 | 187 | The following two metrics are adopted to compare among models' robustness under sensor corruptions: 188 | - **mCE (the lower the better):** The *average corruption error* (in percentage) of a candidate model compared to the baseline model, which is calculated among all corruption types across three severity levels. 189 | - **mRR (the higher the better):** The *average resilience rate* (in percentage) of a candidate model compared to its "clean" performance, which is calculated among all corruption types across three severity levels. 190 | 191 | 192 | ### :red_car:  Camera-Only Benchmarking Results 193 | 194 | | | 195 | | :-: | 196 | 197 | | Model | mCE | mRR | Clean | Camera | Frame | Quant | Motion | Bright | Dark | Fog | Snow | 198 | | :--------------: | :-----: | :-----: |:-----: | :-------: | :--------: | :---------: | :---------: | :----: | :-------: | :----: | :----: | 199 | |**[HDMapNet](https://arxiv.org/abs/2107.06307)** |18.78|43.3|23.0|4.6|5.1|18.9|20.8|16.7|9.3|10.6|5.2| 200 | |**[VectorMapNet](https://arxiv.org/abs/2206.08920)** |148.5|40.6|40.9|13.9|12.3|26.6|29.7|25.2|7.8|18.3|2.9| 201 | |**[PivotNet](https://arxiv.org/pdf/2308.16477)** |96.3|45.2|57.4|17.1|16.7|36.4|34.1|43.5|16.5|37.4|4.6| 202 | |**[BeMapNet](https://openaccess.thecvf.com/content/CVPR2023/html/Qiao_End-to-End_Vectorized_HD-Map_Construction_With_Piecewise_Bezier_Curve_CVPR_2023_paper.html)** |78.5|50.3|59.8|18.8|18.5|38.1|35.3|50.7|23.2|46.5|9.6| 203 | |**[MapTR](https://arxiv.org/abs/2208.14437)** |100.0|49.3|50.3|15.0|14.2|35.4|23.5|44.3|22.7|38.5|3.8| 204 | |**[MapTRv2](https://arxiv.org/abs/2308.05736)** |72.6|51.4|61.5|18.8|18.2|45.3|31.0|54.9|32.3|50.7|1.1| 205 | |**[StreamMapNet](https://arxiv.org/abs/2308.12570)** |64.8|54.4|63.4|13.4|15.5|48.1|44.3|57.0|36.1|52.4|9.1| 206 | |**[HIMap](https://arxiv.org/abs/2308.12570)** |56.9|56.6|65.5|19.4|19.0|52.0|42.5|60.9|40.6|57.1|5.1| 207 | 208 | 209 | ### :blue_car:  LiDAR-Only Benchmarking Results 210 | 211 | | | 212 | | :-: | 213 | 214 | | Model | mCE | mRR | Clean | Fog | Wet | Snow | Motion | Beam | Crosstalk | Echo | Sensor | 215 | | :--------------: | :-----: | :-----: |:-----: | :-------: | :--------: | :---------: | :---------: | :----: | :-------: | :----: | :----: | 216 | |**[VectorMapNet](https://arxiv.org/abs/2206.08920)** |94.9|63.4|34.0|15.7|20.3|15.9|28.8|19.2|19.7|31.3|9.5| 217 | |**[MapTR](https://arxiv.org/abs/2208.14437)** |100.0|55.1|55.6|19.9|19.1|9.6|27.1|16.5|16.3|32.3|6.4| 218 | |**[MapTRv2](https://arxiv.org/abs/2308.05736)** |74.6|57.2|61.5|28.5|29.5|10.3|36.9|27.9|15.4|44.7|14.0| 219 | |**[HIMap](https://arxiv.org/abs/2308.12570)** |73.1|59.2|64.3|26.6|24.6|16.1|37.4|24.4|26.7|43.1|10.8| 220 | 221 | 222 | ### :taxi:  Camera-LiDAR Fusion Benchmarking Results 223 | 224 | | | 225 | | :-: | 226 | 227 | | Model | Modality | Camera | Lidar | APped | APdiv | APbou | mAP | 228 | | :--------------: | :-----: | :-----: |:-----: | :-------: | :--------: | :---------: | :---------: | 229 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L | ✓ | ✓ |55.9|62.3|69.3|62.5| 230 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C | ✓ | — |46.3|51.5|53.1|50.3| 231 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C |Camera Crash | — |18.0|14.5|12.4|15.0| 232 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C |Frame Lost | — |13.9|15.1|13.4|14.2| 233 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L | ✗ | ✓ |15.0|18.2|34.4|22.5| 234 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Camera Crash | ✓ |32.5|36.5|48.4|39.1| 235 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Frame Lost | ✓ |29.1|33.7|46.1|36.3| 236 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | L | — | ✓ |26.6|31.7|41.8|33.4| 237 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | L | — |Incomplete Echo|26.3|29.9|40.6|32.3| 238 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | L | — |Crosstalk |13.6|15.0|20.3|16.3| 239 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | L | — |Cross-Sensor |3.5|6.6|8.9|6.4| 240 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L | ✓ | ✗ |20.7|27.4|13.1|20.4| 241 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L | ✓ |Incomplete Echo|47.9|55.2|62.2|55.1| 242 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L | ✓ |Crosstalk |36.7|42.5|45.3|41.5| 243 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L | ✓ |Cross-Sensor |33.9|42.9|42.0|39.6| 244 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Camera Crash |Incomplete Echo|32.4|35.6|47.8|38.6| 245 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Camera Crash |Crosstalk |19.7|21.6|26.9|22.7| 246 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Camera Crash |Cross-Sensor |18.4|20.8|23.2|20.8| 247 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Frame Lost |Incomplete Echo|28.9|32.8|45.5|35.8| 248 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Frame Lost |Crosstalk |16.9|19.9|25.5|20.8| 249 | |**[MapTR](https://arxiv.org/abs/2208.14437)** | C & L |Frame Lost |Cross-Sensor |15.8|19.4|22.2|19.1| 250 | 251 | | Model | Modality | Camera | Lidar | APped | APdiv | APbou | mAP | 252 | | :--------------: | :-----: | :-----: |:-----: | :-------: | :--------: | :---------: | :---------: | 253 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L | ✓ | ✓ |71.0|72.4|79.4|74.3| 254 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C | ✓ | — |62.2|66.5|67.9|65.5| 255 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C |Camera Crash | — |27.3|19.4|11.6|19.4| 256 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C |Frame Lost | — |21.7|19.1|16.1|19.0| 257 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L | ✗ | ✓ |40.9|46.4|74.7|50.7| 258 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Camera Crash | ✓ |36.3|27.7|20.9|28.3| 259 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Frame Lost | ✓ |29.9|25.0|23.8|26.2| 260 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | L | — | ✓ |54.8|64.7|73.5|64.3| 261 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | L | — |Incomplete Echo|35.4|41.1|52.7|43.1| 262 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | L | — |Crosstalk |20.9|23.8|35.3|26.7| 263 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | L | — |Cross-Sensor |7.8|10.2|14.4|10.8| 264 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L | ✓ | ✗ |30.7|38.7|29.0|32.8| 265 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L | ✓ |Incomplete Echo|59.1|63.7|69.9|64.2| 266 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L | ✓ |Crosstalk |54.1|57.5|63.4|58.3| 267 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L | ✓ |Cross-Sensor |44.2|50.7|50.8|48.5| 268 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Camera Crash |Incomplete Echo|36.2|26.9|20.5|27.9| 269 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Camera Crash |Crosstalk |29.2|19.3|12.9|20.5| 270 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Camera Crash |Cross-Sensor |23.1|13.8|5.9|14.3| 271 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Frame Lost |Incomplete Echo|29.9|24.4|23.5|25.9| 272 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Frame Lost |Crosstalk |23.6|18.9|18.0|20.2| 273 | |**[HIMap](https://arxiv.org/abs/2308.12570)** | C & L |Frame Lost |Cross-Sensor |17.7|14.3|11.2|14.4| 274 | 275 | 276 | 277 | ## :memo: TODO List 278 | - [x] Initial release. 🚀 279 | - [x] Add scripts for creating common corruptions. 280 | - [ ] Add evaluation scripts on corruption sets. 281 | - [ ] ... 282 | 283 | 284 | ## Citation 285 | If you find this work helpful, please kindly consider citing our paper: 286 | 287 | ```bibtex 288 | @article{hao2024mapbench, 289 | author = {Xiaoshuai Hao and Mengchuan Wei and Yifan Yang and Haimei Zhao and Hui Zhang and Yi Zhou and Qiang Wang and Weiming Li and Lingdong Kong and Jing Zhang}, 290 | title = {Is Your HD Map Constructor Reliable under Sensor Corruptions?}, 291 | journal={arXiv preprint arXiv:2406.12214}, 292 | year = {2024}, 293 | } 294 | ``` 295 | 296 | 297 | ## License 298 | 299 | This work is under the [Apache License Version 2.0](https://www.apache.org/licenses/LICENSE-2.0), while some specific operations in this codebase might be with other licenses. Please refer to [LICENSE.md](docs/LICENSE.md) for a more careful check, if you are using our code for commercial matters. 300 | 301 | ## Acknowledgements 302 | 303 | 304 | 305 | 306 | -------------------------------------------------------------------------------- /create/Camera/corruptions.py: -------------------------------------------------------------------------------- 1 | from copy import deepcopy 2 | import functools 3 | import PIL 4 | from PIL import Image 5 | 6 | import torch 7 | import numpy as np 8 | 9 | from mmcv.utils import Registry 10 | from imagecorruptions import corrupt 11 | 12 | 13 | CORRUPTIONS= Registry('corruptions') 14 | 15 | 16 | @CORRUPTIONS.register_module() 17 | class Clean: 18 | def __init__(self, severity, norm_config): 19 | """ 20 | No corruption 21 | """ 22 | self.severity = severity 23 | assert severity >= 1 and severity <= 5, f"Corruption Severity should between (1, 5), now {severity}" 24 | self.norm_config = norm_config 25 | self.corruption = 'clean' 26 | def __call__(self, x): 27 | return x 28 | 29 | 30 | @CORRUPTIONS.register_module() 31 | class BaseCorruption: 32 | def __init__(self, severity, norm_config, corruption): 33 | """ 34 | Base Corruption Class 35 | Args: 36 | severity (int): severity of corruption, range (1, 5) 37 | """ 38 | self.severity = severity 39 | assert severity >= 1 and severity <= 5, f"Corruption Severity should between (1, 5), now {severity}" 40 | self.norm_config = norm_config 41 | self.corruption = corruption 42 | try: 43 | self.corrupt_func = self._get_corrupt_func() 44 | except: 45 | self.corrupt_func = None 46 | 47 | def __call__(self, img): 48 | """ 49 | Args: 50 | img (torch.Tensor): [B, M, C, H, W] 51 | """ 52 | mean = self.norm_config['mean'] 53 | std = self.norm_config['std'] 54 | 55 | img = deepcopy(img) 56 | B, M, C, H, W = img.size() 57 | img = img.permute(0, 1, 3, 4, 2) # [B, M, C, H, W] => [B, M, H, W, C] 58 | img = img * torch.tensor(std) + torch.tensor(mean) 59 | # pixel value [0, 255] 60 | assert img.min() >= 0 and img.max() <= 255, "Image pixel out of range" 61 | new_img = np.zeros_like(img) 62 | for b in range(B): 63 | for m in range(M): 64 | new_img[b, m] = self.corrupt_func(np.uint8(img[b, m].numpy())) 65 | 66 | # new_img = new_img.permute(0, 1, 4, 2, 3) 67 | 68 | return new_img 69 | 70 | def _get_corrupt_func(self): 71 | return functools.partial(corrupt, corruption_name=self.corruption, severity=self.severity) 72 | 73 | 74 | @CORRUPTIONS.register_module() 75 | class DefocusBlur(BaseCorruption): 76 | def __init__(self, severity, norm_config): 77 | """ 78 | Create corruptions: 'Defocus Blur'. 79 | Args: 80 | severity (int): severity of corruption, range (1, 5) 81 | """ 82 | super().__init__(severity, norm_config, 'defocus_blur') 83 | 84 | 85 | @CORRUPTIONS.register_module() 86 | class GlassBlur(BaseCorruption): 87 | def __init__(self, severity, norm_config): 88 | """ 89 | Create corruptions: 'Glass Blur'. 90 | Args: 91 | severity (int): severity of corruption, range (1, 5) 92 | """ 93 | super().__init__(severity, norm_config, 'glass_blur') 94 | 95 | 96 | @CORRUPTIONS.register_module() 97 | class MotionBlur(BaseCorruption): 98 | def __init__(self, severity, norm_config): 99 | """ 100 | Create corruptions: 'Motion Blur'. 101 | Args: 102 | severity (int): severity of corruption, range (1, 5) 103 | """ 104 | super().__init__(severity, norm_config, 'motion_blur') 105 | 106 | 107 | @CORRUPTIONS.register_module() 108 | class ZoomBlur(BaseCorruption): 109 | def __init__(self, severity, norm_config): 110 | """ 111 | Create corruptions: 'Zoom Blur'. 112 | Args: 113 | severity (int): severity of corruption, range (1, 5) 114 | """ 115 | super().__init__(severity, norm_config, 'zoom_blur') 116 | 117 | 118 | @CORRUPTIONS.register_module() 119 | class GaussianNoise(BaseCorruption): 120 | def __init__(self, severity, norm_config): 121 | """ 122 | Create corruptions: 'Gaussian Noise'. 123 | Args: 124 | severity (int): severity of corruption, range (1, 5) 125 | """ 126 | super().__init__(severity, norm_config, 'gaussian_noise') 127 | 128 | 129 | @CORRUPTIONS.register_module() 130 | class ImpulseNoise(BaseCorruption): 131 | def __init__(self, severity, norm_config): 132 | """ 133 | Create corruptions: 'Impulse Noise'. 134 | Args: 135 | severity (int): severity of corruption, range (1, 5) 136 | """ 137 | super().__init__(severity, norm_config, 'impulse_noise') 138 | 139 | 140 | @CORRUPTIONS.register_module() 141 | class ShotNoise(BaseCorruption): 142 | def __init__(self, severity, norm_config): 143 | """ 144 | Create corruptions: 'ISO Noise'. 145 | Args: 146 | severity (int): severity of corruption, range (1, 5) 147 | """ 148 | super().__init__(severity, norm_config, 'shot_noise') 149 | 150 | 151 | @CORRUPTIONS.register_module() 152 | class ISONoise(BaseCorruption): 153 | def __init__(self, severity, norm_config): 154 | """ 155 | Create corruptions: 'Shot Noise'. 156 | Args: 157 | severity (int): severity of corruption, range (1, 5) 158 | """ 159 | super().__init__(severity, norm_config, 'iso_noise') 160 | self.corrupt_func = self._get_corrupt_func() 161 | 162 | def _get_corrupt_func(self): 163 | return functools.partial(self.iso_noise, severity=self.severity) 164 | 165 | def iso_noise(self, x, severity): 166 | c_poisson = 25 167 | x = np.array(x) / 255. 168 | x = np.clip(np.random.poisson(x * c_poisson) / c_poisson, 0, 1) * 255. 169 | c_gauss = 0.7 * [.08, .12, 0.18, 0.26, 0.38][severity] 170 | x = np.array(x) / 255. 171 | x = np.clip(x + np.random.normal(size=x.shape, scale= c_gauss), 0, 1) * 255. 172 | return np.uint8(x) 173 | 174 | 175 | @CORRUPTIONS.register_module() 176 | class Brightness(BaseCorruption): 177 | def __init__(self, severity, norm_config): 178 | """ 179 | Create corruptions: 'Brightness'. 180 | Args: 181 | severity (int): severity of corruption, range (1, 5) 182 | """ 183 | super().__init__(severity, norm_config, 'brightness') 184 | 185 | 186 | @CORRUPTIONS.register_module() 187 | class LowLight(BaseCorruption): 188 | def __init__(self, severity, norm_config): 189 | """ 190 | Create corruptions: 'Dark'. 191 | Args: 192 | severity (int): severity of corruption, range (1, 5) 193 | """ 194 | super().__init__(severity, norm_config, 'dark') 195 | self.corrupt_func = self._get_corrupt_func() 196 | 197 | def _get_corrupt_func(self): 198 | return functools.partial(self.low_light, severity=self.severity) 199 | 200 | def imadjust(self, x, a, b, c, d, gamma=1): 201 | y = (((x - a) / (b - a)) ** gamma) * (d - c) + c 202 | return y 203 | 204 | def poisson_gaussian_noise(self, x, severity): 205 | c_poisson = 10 * [60, 25, 12, 5, 3][severity] 206 | x = np.array(x) / 255. 207 | x = np.clip(np.random.poisson(x * c_poisson) / c_poisson, 0, 1) * 255 208 | c_gauss = 0.1 * [.08, .12, 0.18, 0.26, 0.38][severity] 209 | x = np.array(x) / 255. 210 | x = np.clip(x + np.random.normal(size=x.shape, scale= c_gauss), 0, 1) * 255 211 | return np.uint8(x) 212 | 213 | def low_light(self, x, severity): 214 | c = [0.60, 0.50, 0.40, 0.30, 0.20][severity] 215 | # c = [0.50, 0.40, 0.30, 0.20, 0.10][severity-1] 216 | x = np.array(x) / 255. 217 | x_scaled = self.imadjust(x, x.min(), x.max(), 0, c, gamma=2.) * 255 218 | x_scaled = self.poisson_gaussian_noise(x_scaled, severity=severity) 219 | return x_scaled 220 | 221 | 222 | @CORRUPTIONS.register_module() 223 | class Fog(BaseCorruption): 224 | def __init__(self, severity, norm_config): 225 | """ 226 | Create corruptions: 'Fog'. 227 | Args: 228 | severity (int): severity of corruption, range (1, 5) 229 | """ 230 | super().__init__(severity, norm_config, 'fog') 231 | 232 | 233 | @CORRUPTIONS.register_module() 234 | class Snow(BaseCorruption): 235 | def __init__(self, severity, norm_config): 236 | """ 237 | Create corruptions: 'Snow'. 238 | Args: 239 | severity (int): severity of corruption, range (1, 5) 240 | """ 241 | super().__init__(severity, norm_config, 'snow') 242 | 243 | 244 | @CORRUPTIONS.register_module() 245 | class CameraCrash: 246 | def __init__(self, severity, norm_config): 247 | """ 248 | Create corruptions: 'Camera Crash'. 249 | """ 250 | self.severity = severity 251 | assert severity >= 1 and severity <= 5, f"Corruption Severity should between (1, 5), now {severity}" 252 | self.norm_config = norm_config 253 | self.corruption = 'cam_crash' 254 | self.crash_camera = self.get_crash_camera() 255 | 256 | def __call__(self, img): 257 | """ 258 | Args: 259 | img (torch.Tensor): [B, M, C, H, W] 260 | """ 261 | mean = self.norm_config['mean'] 262 | std = self.norm_config['std'] 263 | 264 | img = deepcopy(img) 265 | B, M, C, H, W = img.size() 266 | img = img.permute(0, 1, 3, 4, 2) # [B, M, C, H, W] => [B, M, H, W, C] 267 | img = img * torch.tensor(std) + torch.tensor(mean) 268 | # pixel value [0, 255] 269 | assert img.min() >= 0 and img.max() <= 255, "Image pixel out of range" 270 | 271 | for b in range(B): 272 | for m in self.crash_camera: 273 | img[b, m] = 0 274 | 275 | assert img.min() >= 0 and img.max() <= 255, "Image pixel out of range" 276 | # img = img - torch.tensor(mean) / torch.tensor(std) 277 | # img = img.permute(0, 1, 4, 2, 3) 278 | 279 | return img.numpy() 280 | 281 | def get_crash_camera(self): 282 | crash_camera = np.random.choice([0, 1, 2, 3, 4, 5], size=self.severity) 283 | return list(crash_camera) 284 | 285 | 286 | @CORRUPTIONS.register_module() 287 | class FrameLost(): 288 | def __init__(self, severity, norm_config): 289 | """ 290 | Create corruptions: 'Frame Lost'. 291 | """ 292 | self.severity = severity 293 | assert severity >= 1 and severity <= 5, f"Corruption Severity should between (1, 5), now {severity}" 294 | self.norm_config = norm_config 295 | self.corruption = 'frame_lost' 296 | 297 | def __call__(self, img): 298 | """ 299 | Args: 300 | img (torch.Tensor): [B, M, C, H, W] 301 | """ 302 | mean = self.norm_config['mean'] 303 | std = self.norm_config['std'] 304 | 305 | img = deepcopy(img) 306 | B, M, C, H, W = img.size() 307 | img = img.permute(0, 1, 3, 4, 2) # [B, M, C, H, W] => [B, M, H, W, C] 308 | img = img * torch.tensor(std) + torch.tensor(mean) 309 | # pixel value [0, 255] 310 | assert img.min() >= 0 and img.max() <= 255, "Image pixel out of range" 311 | 312 | for b in range(B): 313 | for m in range(M): 314 | if np.random.rand() < (self.severity * 1. / 6.): 315 | img[b, m] = 0 316 | 317 | assert img.min() >= 0 and img.max() <= 255, "Image pixel out of range" 318 | # img = img - torch.tensor(mean) / torch.tensor(std) 319 | # img = img.permute(0, 1, 4, 2, 3) 320 | 321 | return img.numpy() 322 | 323 | 324 | @CORRUPTIONS.register_module() 325 | class ColorQuant(BaseCorruption): 326 | def __init__(self, severity, norm_config): 327 | """ 328 | Create corruptions: 'Color Quantization'. 329 | Args: 330 | severity (int): severity of corruption, range (1, 5) 331 | """ 332 | super().__init__(severity, norm_config, 'color_quant') 333 | 334 | def _get_corrupt_func(self): 335 | return functools.partial(self.color_quant, severity=self.severity) 336 | 337 | def color_quant(self, x, severity): 338 | bits = 5 - severity 339 | x = Image.fromarray(np.uint8(x)) 340 | x = PIL.ImageOps.posterize(x, bits) 341 | return np.asarray(x) 342 | 343 | 344 | @CORRUPTIONS.register_module() 345 | class Pixlate(BaseCorruption): 346 | def __init__(self, severity, norm_config): 347 | """ 348 | Create corruptions: 'Pixelate'. 349 | Args: 350 | severity (int): severity of corruption, range (1, 5) 351 | """ 352 | super().__init__(severity, norm_config, 'pixelate') -------------------------------------------------------------------------------- /create/LiDAR/cross_sensor/cross_sensor.sh: -------------------------------------------------------------------------------- 1 | CUDA_VISIBLE_DEVICES=0 python gen_cross_sensor.py \ 2 | --root_folder ./data_root/nuScenes \ 3 | --dst_folder ./save_root/cross_sensor/light \ 4 | --num_beam_to_drop 8 -------------------------------------------------------------------------------- /create/LiDAR/cross_sensor/gen_cross_sensor.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import os 3 | import random 4 | import time 5 | import glob 6 | import multiprocessing as mp 7 | import copy 8 | from pathlib import Path 9 | from tqdm import tqdm 10 | from nuscenes import NuScenes 11 | import pickle 12 | import numpy as np 13 | 14 | seed = 1205 15 | random.seed(seed) 16 | np.random.seed(seed) 17 | 18 | 19 | 20 | 21 | def parse_arguments(): 22 | 23 | parser = argparse.ArgumentParser(description='LiDAR cross_sensor') 24 | parser.add_argument('-c', '--n_cpus', help='number of CPUs that should be used', type=int, default= mp.cpu_count()) 25 | parser.add_argument('-f', '--n_features', help='number of point features', type=int, default=4) 26 | parser.add_argument('-r', '--root_folder', help='root folder of dataset', 27 | default='./data_root/nuScenes') 28 | parser.add_argument('-d', '--dst_folder', help='savefolder of dataset', type=str, 29 | default='./save_root/cross_sensor/light') # ['light','moderate','heavy'] 30 | parser.add_argument('-n', '--num_beam_to_drop', help='number of beam to be dropped', type=int, default=8) 31 | arguments = parser.parse_args() 32 | 33 | return arguments 34 | 35 | 36 | 37 | 38 | 39 | if __name__ == '__main__': 40 | args = parse_arguments() 41 | num_beam_to_drop = args.num_beam_to_drop 42 | print(num_beam_to_drop) 43 | print('') 44 | print(f'using {args.n_cpus} CPUs') 45 | 46 | all_files = [] 47 | nusc_info = NuScenes(version='v1.0-trainval', dataroot=args.root_folder, verbose=False) 48 | imageset = os.path.join(args.root_folder,"nuscenes_infos_val.pkl") 49 | with open(imageset, 'rb') as f: 50 | infos = pickle.load(f) 51 | all_files = infos['infos'] 52 | 53 | all_paths = copy.deepcopy(all_files) 54 | dst_folder = args.dst_folder 55 | 56 | Path(dst_folder).mkdir(parents=True, exist_ok=True) 57 | 58 | lidar_save_root = os.path.join(dst_folder, 'samples/LIDAR_TOP') 59 | if not os.path.exists(lidar_save_root): 60 | os.makedirs(lidar_save_root) 61 | label_save_root = os.path.join(dst_folder, 'lidarseg/v1.0-trainval') 62 | if not os.path.exists(label_save_root): 63 | os.makedirs(label_save_root) 64 | 65 | def _map(i: int) -> None: 66 | info = all_paths[i] 67 | lidar_path = info['lidar_path'][16:] 68 | scan = np.fromfile(os.path.join(args.root_folder, lidar_path), dtype=np.float32, count=-1).reshape([-1, 5]) 69 | 70 | lidar_sd_token = nusc_info.get('sample', info['token'])['data']['LIDAR_TOP'] 71 | label_path = nusc_info.get('lidarseg', lidar_sd_token)['filename'] 72 | lidarseg_labels_filename = os.path.join(args.root_folder, label_path) 73 | label = np.fromfile(lidarseg_labels_filename, dtype=np.uint8).reshape(-1) 74 | 75 | # get beam id 76 | beam_id = scan[:,-1] 77 | beam_id = beam_id.astype(np.int64) 78 | 79 | if num_beam_to_drop == 8: 80 | to_drop = np.arange(1, 32, 4) 81 | assert len(to_drop) == 8 82 | 83 | elif num_beam_to_drop == 16: 84 | to_drop = np.arange(1, 32, 2) 85 | assert len(to_drop) == 16 86 | 87 | elif num_beam_to_drop == 24: 88 | to_drop = np.arange(1, 32, 1.33) 89 | to_drop = to_drop.astype(int) 90 | assert len(to_drop) == 24 91 | 92 | to_keep = [i for i in np.arange(0, 32, 1) if i not in to_drop] 93 | assert len(to_drop) + len(to_keep) == 32 94 | 95 | 96 | for id in to_drop: 97 | points_to_drop = beam_id == id 98 | 99 | scan = np.delete(scan, points_to_drop, axis=0) 100 | label = np.delete(label, points_to_drop, axis=0) 101 | assert len(scan) == len(label) 102 | 103 | beam_id = np.delete(beam_id, points_to_drop, axis=0) 104 | 105 | 106 | scan = scan[::2, :] 107 | label = label[::2] 108 | 109 | assert len(scan) == len(label) 110 | 111 | lidar_save_path = os.path.join(dst_folder, lidar_path) 112 | label_save_path = os.path.join(dst_folder, label_path ) 113 | 114 | scan.astype(np.float32).tofile(lidar_save_path) 115 | label.astype(np.uint8).tofile(label_save_path) 116 | 117 | n = len(all_files) 118 | 119 | with mp.Pool(args.n_cpus) as pool: 120 | 121 | l = list(tqdm(pool.imap(_map, range(n)), total=n)) 122 | 123 | 124 | -------------------------------------------------------------------------------- /create/LiDAR/crosstalk/crosstalk.sh: -------------------------------------------------------------------------------- 1 | CUDA_VISIBLE_DEVICES=0 python gen_crosstalk.py \ 2 | --root_folder ./data_root/nuScenes \ 3 | --dst_folder ./save_root/crosstalk/light \ 4 | --percentage 0.03 -------------------------------------------------------------------------------- /create/LiDAR/crosstalk/gen_crosstalk.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import os 3 | import time 4 | import glob 5 | import numpy as np 6 | import multiprocessing as mp 7 | import copy 8 | from pathlib import Path 9 | from tqdm import tqdm 10 | from nuscenes import NuScenes 11 | import pickle 12 | import random 13 | 14 | seed = 1205 15 | random.seed(seed) 16 | np.random.seed(seed) 17 | import yaml 18 | 19 | 20 | def parse_arguments(): 21 | parser = argparse.ArgumentParser(description='LiDAR crosstalk') 22 | parser.add_argument('-c', '--n_cpus', help='number of CPUs that should be used', type=int, default=mp.cpu_count()) 23 | parser.add_argument('-f', '--n_features', help='number of point features', type=int, default=4) 24 | parser.add_argument('-r', '--root_folder', help='root folder of dataset', 25 | default='./data_root/nuScenes') 26 | parser.add_argument('-d', '--dst_folder', help='savefolder of dataset', type=str, 27 | default='./save_root/crosstalk/light') # ['light','moderate','heavy'] 28 | parser.add_argument('-p', '--percentage', help='crosstalk ratio', type=float, default=0.03) 29 | arguments = parser.parse_args() 30 | 31 | return arguments 32 | 33 | 34 | def lidar_crosstalk_noise(pointcloud, percentage): 35 | 36 | N, C = pointcloud.shape # [m,], 4 (xyzi) 37 | c = int(percentage * N) 38 | index = np.random.choice(N, c, replace=False) 39 | pointcloud[index] += np.random.normal(size=(c, C)) * 3.0 40 | 41 | return pointcloud, index 42 | 43 | 44 | 45 | 46 | if __name__ == '__main__': 47 | args = parse_arguments() 48 | percentage = args.percentage 49 | print(percentage) 50 | print('') 51 | print(f'using {args.n_cpus} CPUs') 52 | 53 | all_files = [] 54 | nusc_info = NuScenes(version='v1.0-trainval', dataroot=args.root_folder, verbose=False) 55 | imageset = os.path.join(args.root_folder,"nuscenes_infos_val.pkl") 56 | with open(imageset, 'rb') as f: 57 | infos = pickle.load(f) 58 | all_files = infos['infos'] 59 | 60 | all_paths = copy.deepcopy(all_files) 61 | dst_folder = args.dst_folder 62 | 63 | Path(dst_folder).mkdir(parents=True, exist_ok=True) 64 | lidar_save_root = os.path.join(dst_folder, 'samples/LIDAR_TOP') 65 | if not os.path.exists(lidar_save_root): 66 | os.makedirs(lidar_save_root) 67 | 68 | 69 | label_save_root = os.path.join(dst_folder, 'lidarseg/v1.0-trainval') 70 | if not os.path.exists(label_save_root): 71 | os.makedirs(label_save_root) 72 | 73 | 74 | def _map(i: int) -> None: 75 | info = all_paths[i] 76 | lidar_path = info['lidar_path'][16:] 77 | scan = np.fromfile(os.path.join(args.root_folder, lidar_path), dtype=np.float32, count=-1).reshape([-1, 5]) 78 | 79 | lidar_sd_token = nusc_info.get('sample', info['token'])['data']['LIDAR_TOP'] 80 | label_path = nusc_info.get('lidarseg', lidar_sd_token)['filename'] 81 | lidarseg_labels_filename = os.path.join(args.root_folder, label_path) 82 | sem_label = np.fromfile(lidarseg_labels_filename, dtype=np.uint8).reshape(-1) 83 | 84 | 85 | crosstalk_scan, index = lidar_crosstalk_noise(scan[:,:-1], percentage=percentage) 86 | crosstalk_scan = np.concatenate((crosstalk_scan, scan[:, -1].reshape(-1,1)), axis=1) 87 | assert crosstalk_scan.shape[1] == 5 88 | 89 | sem_label[index] = 43 # ignored (crosstalk) 90 | 91 | sem_label = sem_label.reshape(-1,1) 92 | 93 | lidar_save_path = os.path.join(dst_folder, lidar_path) 94 | label_save_path = os.path.join(dst_folder, label_path ) 95 | 96 | crosstalk_scan.astype(np.float32).tofile(lidar_save_path) 97 | 98 | sem_label = sem_label.reshape(-1,1) 99 | sem_label.astype(np.uint8).tofile(label_save_path) 100 | 101 | 102 | 103 | 104 | n = len(all_files) 105 | 106 | with mp.Pool(args.n_cpus) as pool: 107 | 108 | l = list(tqdm(pool.imap(_map, range(n)), total=n)) 109 | 110 | 111 | 112 | 113 | 114 | -------------------------------------------------------------------------------- /create/LiDAR/fog/LICENSE: -------------------------------------------------------------------------------- 1 | Attribution-NonCommercial 4.0 International 2 | 3 | ======================================================================= 4 | 5 | Creative Commons Corporation ("Creative Commons") is not a law firm and 6 | does not provide legal services or legal advice. Distribution of 7 | Creative Commons public licenses does not create a lawyer-client or 8 | other relationship. Creative Commons makes its licenses and related 9 | information available on an "as-is" basis. Creative Commons gives no 10 | warranties regarding its licenses, any material licensed under their 11 | terms and conditions, or any related information. Creative Commons 12 | disclaims all liability for damages resulting from their use to the 13 | fullest extent possible. 14 | 15 | Using Creative Commons Public Licenses 16 | 17 | Creative Commons public licenses provide a standard set of terms and 18 | conditions that creators and other rights holders may use to share 19 | original works of authorship and other material subject to copyright 20 | and certain other rights specified in the public license below. The 21 | following considerations are for informational purposes only, are not 22 | exhaustive, and do not form part of our licenses. 23 | 24 | Considerations for licensors: Our public licenses are 25 | intended for use by those authorized to give the public 26 | permission to use material in ways otherwise restricted by 27 | copyright and certain other rights. Our licenses are 28 | irrevocable. Licensors should read and understand the terms 29 | and conditions of the license they choose before applying it. 30 | Licensors should also secure all rights necessary before 31 | applying our licenses so that the public can reuse the 32 | material as expected. Licensors should clearly mark any 33 | material not subject to the license. This includes other CC- 34 | licensed material, or material used under an exception or 35 | limitation to copyright. More considerations for licensors: 36 | wiki.creativecommons.org/Considerations_for_licensors 37 | 38 | Considerations for the public: By using one of our public 39 | licenses, a licensor grants the public permission to use the 40 | licensed material under specified terms and conditions. If 41 | the licensor's permission is not necessary for any reason--for 42 | example, because of any applicable exception or limitation to 43 | copyright--then that use is not regulated by the license. Our 44 | licenses grant only permissions under copyright and certain 45 | other rights that a licensor has authority to grant. Use of 46 | the licensed material may still be restricted for other 47 | reasons, including because others have copyright or other 48 | rights in the material. A licensor may make special requests, 49 | such as asking that all changes be marked or described. 50 | Although not required by our licenses, you are encouraged to 51 | respect those requests where reasonable. More_considerations 52 | for the public: 53 | wiki.creativecommons.org/Considerations_for_licensees 54 | 55 | ======================================================================= 56 | 57 | Creative Commons Attribution-NonCommercial 4.0 International Public 58 | License 59 | 60 | By exercising the Licensed Rights (defined below), You accept and agree 61 | to be bound by the terms and conditions of this Creative Commons 62 | Attribution-NonCommercial 4.0 International Public License ("Public 63 | License"). To the extent this Public License may be interpreted as a 64 | contract, You are granted the Licensed Rights in consideration of Your 65 | acceptance of these terms and conditions, and the Licensor grants You 66 | such rights in consideration of benefits the Licensor receives from 67 | making the Licensed Material available under these terms and 68 | conditions. 69 | 70 | 71 | Section 1 -- Definitions. 72 | 73 | a. Adapted Material means material subject to Copyright and Similar 74 | Rights that is derived from or based upon the Licensed Material 75 | and in which the Licensed Material is translated, altered, 76 | arranged, transformed, or otherwise modified in a manner requiring 77 | permission under the Copyright and Similar Rights held by the 78 | Licensor. For purposes of this Public License, where the Licensed 79 | Material is a musical work, performance, or sound recording, 80 | Adapted Material is always produced where the Licensed Material is 81 | synched in timed relation with a moving image. 82 | 83 | b. Adapter's License means the license You apply to Your Copyright 84 | and Similar Rights in Your contributions to Adapted Material in 85 | accordance with the terms and conditions of this Public License. 86 | 87 | c. Copyright and Similar Rights means copyright and/or similar rights 88 | closely related to copyright including, without limitation, 89 | performance, broadcast, sound recording, and Sui Generis Database 90 | Rights, without regard to how the rights are labeled or 91 | categorized. For purposes of this Public License, the rights 92 | specified in Section 2(b)(1)-(2) are not Copyright and Similar 93 | Rights. 94 | d. Effective Technological Measures means those measures that, in the 95 | absence of proper authority, may not be circumvented under laws 96 | fulfilling obligations under Article 11 of the WIPO Copyright 97 | Treaty adopted on December 20, 1996, and/or similar international 98 | agreements. 99 | 100 | e. Exceptions and Limitations means fair use, fair dealing, and/or 101 | any other exception or limitation to Copyright and Similar Rights 102 | that applies to Your use of the Licensed Material. 103 | 104 | f. Licensed Material means the artistic or literary work, database, 105 | or other material to which the Licensor applied this Public 106 | License. 107 | 108 | g. Licensed Rights means the rights granted to You subject to the 109 | terms and conditions of this Public License, which are limited to 110 | all Copyright and Similar Rights that apply to Your use of the 111 | Licensed Material and that the Licensor has authority to license. 112 | 113 | h. Licensor means the individual(s) or entity(ies) granting rights 114 | under this Public License. 115 | 116 | i. NonCommercial means not primarily intended for or directed towards 117 | commercial advantage or monetary compensation. For purposes of 118 | this Public License, the exchange of the Licensed Material for 119 | other material subject to Copyright and Similar Rights by digital 120 | file-sharing or similar means is NonCommercial provided there is 121 | no payment of monetary compensation in connection with the 122 | exchange. 123 | 124 | j. Share means to provide material to the public by any means or 125 | process that requires permission under the Licensed Rights, such 126 | as reproduction, public display, public performance, distribution, 127 | dissemination, communication, or importation, and to make material 128 | available to the public including in ways that members of the 129 | public may access the material from a place and at a time 130 | individually chosen by them. 131 | 132 | k. Sui Generis Database Rights means rights other than copyright 133 | resulting from Directive 96/9/EC of the European Parliament and of 134 | the Council of 11 March 1996 on the legal protection of databases, 135 | as amended and/or succeeded, as well as other essentially 136 | equivalent rights anywhere in the world. 137 | 138 | l. You means the individual or entity exercising the Licensed Rights 139 | under this Public License. Your has a corresponding meaning. 140 | 141 | 142 | Section 2 -- Scope. 143 | 144 | a. License grant. 145 | 146 | 1. Subject to the terms and conditions of this Public License, 147 | the Licensor hereby grants You a worldwide, royalty-free, 148 | non-sublicensable, non-exclusive, irrevocable license to 149 | exercise the Licensed Rights in the Licensed Material to: 150 | 151 | a. reproduce and Share the Licensed Material, in whole or 152 | in part, for NonCommercial purposes only; and 153 | 154 | b. produce, reproduce, and Share Adapted Material for 155 | NonCommercial purposes only. 156 | 157 | 2. Exceptions and Limitations. For the avoidance of doubt, where 158 | Exceptions and Limitations apply to Your use, this Public 159 | License does not apply, and You do not need to comply with 160 | its terms and conditions. 161 | 162 | 3. Term. The term of this Public License is specified in Section 163 | 6(a). 164 | 165 | 4. Media and formats; technical modifications allowed. The 166 | Licensor authorizes You to exercise the Licensed Rights in 167 | all media and formats whether now known or hereafter created, 168 | and to make technical modifications necessary to do so. The 169 | Licensor waives and/or agrees not to assert any right or 170 | authority to forbid You from making technical modifications 171 | necessary to exercise the Licensed Rights, including 172 | technical modifications necessary to circumvent Effective 173 | Technological Measures. For purposes of this Public License, 174 | simply making modifications authorized by this Section 2(a) 175 | (4) never produces Adapted Material. 176 | 177 | 5. Downstream recipients. 178 | 179 | a. Offer from the Licensor -- Licensed Material. Every 180 | recipient of the Licensed Material automatically 181 | receives an offer from the Licensor to exercise the 182 | Licensed Rights under the terms and conditions of this 183 | Public License. 184 | 185 | b. No downstream restrictions. You may not offer or impose 186 | any additional or different terms or conditions on, or 187 | apply any Effective Technological Measures to, the 188 | Licensed Material if doing so restricts exercise of the 189 | Licensed Rights by any recipient of the Licensed 190 | Material. 191 | 192 | 6. No endorsement. Nothing in this Public License constitutes or 193 | may be construed as permission to assert or imply that You 194 | are, or that Your use of the Licensed Material is, connected 195 | with, or sponsored, endorsed, or granted official status by, 196 | the Licensor or others designated to receive attribution as 197 | provided in Section 3(a)(1)(A)(i). 198 | 199 | b. Other rights. 200 | 201 | 1. Moral rights, such as the right of integrity, are not 202 | licensed under this Public License, nor are publicity, 203 | privacy, and/or other similar personality rights; however, to 204 | the extent possible, the Licensor waives and/or agrees not to 205 | assert any such rights held by the Licensor to the limited 206 | extent necessary to allow You to exercise the Licensed 207 | Rights, but not otherwise. 208 | 209 | 2. Patent and trademark rights are not licensed under this 210 | Public License. 211 | 212 | 3. To the extent possible, the Licensor waives any right to 213 | collect royalties from You for the exercise of the Licensed 214 | Rights, whether directly or through a collecting society 215 | under any voluntary or waivable statutory or compulsory 216 | licensing scheme. In all other cases the Licensor expressly 217 | reserves any right to collect such royalties, including when 218 | the Licensed Material is used other than for NonCommercial 219 | purposes. 220 | 221 | 222 | Section 3 -- License Conditions. 223 | 224 | Your exercise of the Licensed Rights is expressly made subject to the 225 | following conditions. 226 | 227 | a. Attribution. 228 | 229 | 1. If You Share the Licensed Material (including in modified 230 | form), You must: 231 | 232 | a. retain the following if it is supplied by the Licensor 233 | with the Licensed Material: 234 | 235 | i. identification of the creator(s) of the Licensed 236 | Material and any others designated to receive 237 | attribution, in any reasonable manner requested by 238 | the Licensor (including by pseudonym if 239 | designated); 240 | 241 | ii. a copyright notice; 242 | 243 | iii. a notice that refers to this Public License; 244 | 245 | iv. a notice that refers to the disclaimer of 246 | warranties; 247 | 248 | v. a URI or hyperlink to the Licensed Material to the 249 | extent reasonably practicable; 250 | 251 | b. indicate if You modified the Licensed Material and 252 | retain an indication of any previous modifications; and 253 | 254 | c. indicate the Licensed Material is licensed under this 255 | Public License, and include the text of, or the URI or 256 | hyperlink to, this Public License. 257 | 258 | 2. You may satisfy the conditions in Section 3(a)(1) in any 259 | reasonable manner based on the medium, means, and context in 260 | which You Share the Licensed Material. For example, it may be 261 | reasonable to satisfy the conditions by providing a URI or 262 | hyperlink to a resource that includes the required 263 | information. 264 | 265 | 3. If requested by the Licensor, You must remove any of the 266 | information required by Section 3(a)(1)(A) to the extent 267 | reasonably practicable. 268 | 269 | 4. If You Share Adapted Material You produce, the Adapter's 270 | License You apply must not prevent recipients of the Adapted 271 | Material from complying with this Public License. 272 | 273 | 274 | Section 4 -- Sui Generis Database Rights. 275 | 276 | Where the Licensed Rights include Sui Generis Database Rights that 277 | apply to Your use of the Licensed Material: 278 | 279 | a. for the avoidance of doubt, Section 2(a)(1) grants You the right 280 | to extract, reuse, reproduce, and Share all or a substantial 281 | portion of the contents of the database for NonCommercial purposes 282 | only; 283 | 284 | b. if You include all or a substantial portion of the database 285 | contents in a database in which You have Sui Generis Database 286 | Rights, then the database in which You have Sui Generis Database 287 | Rights (but not its individual contents) is Adapted Material; and 288 | 289 | c. You must comply with the conditions in Section 3(a) if You Share 290 | all or a substantial portion of the contents of the database. 291 | 292 | For the avoidance of doubt, this Section 4 supplements and does not 293 | replace Your obligations under this Public License where the Licensed 294 | Rights include other Copyright and Similar Rights. 295 | 296 | 297 | Section 5 -- Disclaimer of Warranties and Limitation of Liability. 298 | 299 | a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE 300 | EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS 301 | AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF 302 | ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS, 303 | IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION, 304 | WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR 305 | PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS, 306 | ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT 307 | KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT 308 | ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU. 309 | 310 | b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE 311 | TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION, 312 | NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT, 313 | INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES, 314 | COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR 315 | USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN 316 | ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR 317 | DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR 318 | IN PART, THIS LIMITATION MAY NOT APPLY TO YOU. 319 | 320 | c. The disclaimer of warranties and limitation of liability provided 321 | above shall be interpreted in a manner that, to the extent 322 | possible, most closely approximates an absolute disclaimer and 323 | waiver of all liability. 324 | 325 | 326 | Section 6 -- Term and Termination. 327 | 328 | a. This Public License applies for the term of the Copyright and 329 | Similar Rights licensed here. However, if You fail to comply with 330 | this Public License, then Your rights under this Public License 331 | terminate automatically. 332 | 333 | b. Where Your right to use the Licensed Material has terminated under 334 | Section 6(a), it reinstates: 335 | 336 | 1. automatically as of the date the violation is cured, provided 337 | it is cured within 30 days of Your discovery of the 338 | violation; or 339 | 340 | 2. upon express reinstatement by the Licensor. 341 | 342 | For the avoidance of doubt, this Section 6(b) does not affect any 343 | right the Licensor may have to seek remedies for Your violations 344 | of this Public License. 345 | 346 | c. For the avoidance of doubt, the Licensor may also offer the 347 | Licensed Material under separate terms or conditions or stop 348 | distributing the Licensed Material at any time; however, doing so 349 | will not terminate this Public License. 350 | 351 | d. Sections 1, 5, 6, 7, and 8 survive termination of this Public 352 | License. 353 | 354 | 355 | Section 7 -- Other Terms and Conditions. 356 | 357 | a. The Licensor shall not be bound by any additional or different 358 | terms or conditions communicated by You unless expressly agreed. 359 | 360 | b. Any arrangements, understandings, or agreements regarding the 361 | Licensed Material not stated herein are separate from and 362 | independent of the terms and conditions of this Public License. 363 | 364 | 365 | Section 8 -- Interpretation. 366 | 367 | a. For the avoidance of doubt, this Public License does not, and 368 | shall not be interpreted to, reduce, limit, restrict, or impose 369 | conditions on any use of the Licensed Material that could lawfully 370 | be made without permission under this Public License. 371 | 372 | b. To the extent possible, if any provision of this Public License is 373 | deemed unenforceable, it shall be automatically reformed to the 374 | minimum extent necessary to make it enforceable. If the provision 375 | cannot be reformed, it shall be severed from this Public License 376 | without affecting the enforceability of the remaining terms and 377 | conditions. 378 | 379 | c. No term or condition of this Public License will be waived and no 380 | failure to comply consented to unless expressly agreed to by the 381 | Licensor. 382 | 383 | d. Nothing in this Public License constitutes or may be interpreted 384 | as a limitation upon, or waiver of, any privileges and immunities 385 | that apply to the Licensor or You, including from the legal 386 | processes of any jurisdiction or authority. 387 | 388 | ======================================================================= 389 | 390 | Creative Commons is not a party to its public 391 | licenses. Notwithstanding, Creative Commons may elect to apply one of 392 | its public licenses to material it publishes and in those instances 393 | will be considered the “Licensor.” The text of the Creative Commons 394 | public licenses is dedicated to the public domain under the CC0 Public 395 | Domain Dedication. Except for the limited purpose of indicating that 396 | material is shared under a Creative Commons public license or as 397 | otherwise permitted by the Creative Commons policies published at 398 | creativecommons.org/policies, Creative Commons does not authorize the 399 | use of the trademark "Creative Commons" or any other trademark or logo 400 | of Creative Commons without its prior written consent including, 401 | without limitation, in connection with any unauthorized modifications 402 | to any of its public licenses or any other arrangements, 403 | understandings, or agreements concerning use of licensed material. For 404 | the avoidance of doubt, this paragraph does not form part of the 405 | public licenses. 406 | 407 | Creative Commons may be contacted at creativecommons.org. 408 | 409 | -------------------------------------------------------------------------------- /create/LiDAR/fog/generate_integral_lookup_table.py: -------------------------------------------------------------------------------- 1 | __author__ = "Martin Hahner" 2 | __contact__ = "martin.hahner@pm.me" 3 | __license__ = "CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)" 4 | 5 | import pickle 6 | import argparse 7 | import functools 8 | 9 | import numpy as np 10 | import multiprocessing as mp 11 | 12 | from tqdm import tqdm 13 | from typing import List 14 | from pathlib import Path 15 | from theory import ParameterSet, P_R_fog_soft 16 | 17 | from scipy.constants import speed_of_light as c # in m/s 18 | 19 | 20 | 21 | def parse_arguments(): 22 | 23 | parser = argparse.ArgumentParser(description='LiDAR foggification') 24 | 25 | parser.add_argument('-a', '--alphas', help='list of alpha values', type=List[float]) 26 | parser.add_argument('-c', '--n_cpus', help='number of CPUs that should be used', type=int, default=mp.cpu_count()) 27 | parser.add_argument('-r', '--r_0_max', help='maximum range', type=int, default=200) 28 | parser.add_argument('-n', '--n_steps', help='number of steps in range interval', type=int) 29 | parser.add_argument('--shift', help='toggle to incorporate shift', type=bool, default=False) 30 | parser.add_argument('-s', '--save_path', help='path to ', 31 | default=str(Path(__file__).parent.absolute() / 'integral_lookup_tables_seg_light_0.008beta/original')) 32 | 33 | arguments = parser.parse_args() 34 | 35 | if arguments.n_steps is None: 36 | arguments.n_steps = 10 * arguments.r_0_max # decimeter accuracy 37 | 38 | if arguments.alphas is None: 39 | arguments.alphas = [0.0, 0.005, 0.01, 0.02, 0.03, 0.06] 40 | 41 | return arguments 42 | 43 | 44 | def P_R_fog_soft_wrapper(p, R: float, n: int = None) -> float: 45 | 46 | if R > p.r_0: 47 | return 0 # skip unnecessary computation 48 | else: 49 | return P_R_fog_soft(p, R, n) 50 | 51 | 52 | def generate_integral_lookup_tables(arguments) -> None: 53 | 54 | for alpha in arguments.alphas: 55 | 56 | n = arguments.n_steps 57 | r_0_max = arguments.r_0_max 58 | 59 | save_path = Path(arguments.save_path) 60 | pool = mp.Pool(arguments.n_cpus) 61 | granularity = r_0_max / n 62 | 63 | filename = f'integral_0m_to_{r_0_max}m_stepsize_{granularity}m_tau_h_20ns_alpha_{alpha}.pickle' 64 | filepath = save_path / filename 65 | 66 | print(f'generating {filepath}') 67 | 68 | p = ParameterSet(n=n, r_range=r_0_max, alpha=alpha) 69 | print(p.beta * 1) 70 | 71 | integral = {} 72 | r_0 = 0 73 | 74 | steps = int(r_0_max / granularity) 75 | 76 | for _ in tqdm(range(steps + 1)): 77 | 78 | p.r_0 = round(r_0, 2) 79 | 80 | x_list = np.linspace(0, p.r_range, p.n) 81 | y_list = pool.map(functools.partial(P_R_fog_soft_wrapper, p), x_list) 82 | 83 | if arguments.shift: 84 | # shift x so that the peak of the transmitted pulse is at t=0 85 | # and the peak response of the hard target is at R_0 86 | x_list = x_list - p.tau_h * c / 2 87 | 88 | argmax = np.argmax(y_list) 89 | 90 | fog_distance = x_list[argmax] 91 | fog_response = y_list[argmax] 92 | 93 | fog_integral = fog_response / (p.c_a * p.p_0 * p.beta) 94 | 95 | integral[p.r_0] = (fog_distance, fog_integral) 96 | 97 | r_0 += granularity 98 | 99 | with open(filepath, 'wb') as f: 100 | pickle.dump(integral, f, protocol=pickle.HIGHEST_PROTOCOL) 101 | 102 | 103 | if __name__ == "__main__": 104 | 105 | args = parse_arguments() 106 | 107 | generate_integral_lookup_tables(arguments=args) 108 | -------------------------------------------------------------------------------- /create/LiDAR/motion_blur/gen_motion.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import os 3 | import random 4 | import time 5 | import glob 6 | import numpy as np 7 | import multiprocessing as mp 8 | import copy 9 | from pathlib import Path 10 | from tqdm import tqdm 11 | from nuscenes import NuScenes 12 | import pickle 13 | 14 | seed = 1205 15 | random.seed(seed) 16 | np.random.seed(seed) 17 | 18 | 19 | def parse_arguments(): 20 | 21 | parser = argparse.ArgumentParser(description='LiDAR motion blur') 22 | parser.add_argument('-c', '--n_cpus', help='number of CPUs that should be used', type=int, default= mp.cpu_count()) 23 | parser.add_argument('-f', '--n_features', help='number of point features', type=int, default=4) 24 | parser.add_argument('-r', '--root_folder', help='root folder of dataset', 25 | default='/data_root/nuScenes') 26 | parser.add_argument('-d', '--dst_folder', help='savefolder of dataset', type=str, 27 | default='./save_root/motion_blur/light') # ['light','moderate','heavy'] 28 | parser.add_argument('-t', '--trans_std', help='jitter score', type=float, default=0.2) 29 | arguments = parser.parse_args() 30 | 31 | return arguments 32 | 33 | 34 | 35 | 36 | 37 | if __name__ == '__main__': 38 | args = parse_arguments() 39 | # motion (jitter score) 40 | trans_std = [args.trans_std]*3 41 | print(trans_std) 42 | print('') 43 | print(f'using {args.n_cpus} CPUs') 44 | 45 | all_files = [] 46 | nusc_info = NuScenes(version='v1.0-trainval', dataroot=args.root_folder, verbose=False) 47 | imageset = os.path.join(args.root_folder,"nuscenes_infos_val.pkl") 48 | with open(imageset, 'rb') as f: 49 | infos = pickle.load(f) 50 | all_files = infos['infos'] 51 | 52 | all_paths = copy.deepcopy(all_files) 53 | dst_folder = args.dst_folder 54 | 55 | Path(dst_folder).mkdir(parents=True, exist_ok=True) 56 | 57 | lidar_save_root = os.path.join(dst_folder, 'samples/LIDAR_TOP') 58 | if not os.path.exists(lidar_save_root): 59 | os.makedirs(lidar_save_root) 60 | 61 | 62 | label_save_root = os.path.join(dst_folder, 'lidarseg/v1.0-trainval') 63 | if not os.path.exists(label_save_root): 64 | os.makedirs(label_save_root) 65 | 66 | 67 | def _map(i: int) -> None: 68 | info = all_paths[i] 69 | lidar_path = info['lidar_path'][16:] 70 | points = np.fromfile(os.path.join(args.root_folder, lidar_path), dtype=np.float32, count=-1).reshape([-1, 5]) #[:, :4] 71 | 72 | lidar_sd_token = nusc_info.get('sample', info['token'])['data']['LIDAR_TOP'] 73 | label_path = nusc_info.get('lidarseg', lidar_sd_token)['filename'] 74 | lidarseg_labels_filename = os.path.join(args.root_folder, label_path) 75 | sem_label = np.fromfile(lidarseg_labels_filename, dtype=np.uint8).reshape(-1, 1) 76 | 77 | noise_translate = np.array([ 78 | np.random.normal(0, trans_std[0], 1), 79 | np.random.normal(0, trans_std[1], 1), 80 | np.random.normal(0, trans_std[2], 1), 81 | ]).T 82 | 83 | points[:, 0:3] += noise_translate 84 | num_points = points.shape[0] 85 | jitters_x = np.clip(np.random.normal(loc=0.0, scale=trans_std[0]*0.1, size=num_points), -3 * trans_std[0], 3 * trans_std[0]) 86 | jitters_y = np.clip(np.random.normal(loc=0.0, scale=trans_std[1]*0.1, size=num_points), -3 * trans_std[1], 3 * trans_std[1]) 87 | jitters_z = np.clip(np.random.normal(loc=0.0, scale=trans_std[2]*0.05, size=num_points), -3 * trans_std[2], 3 * trans_std[2]) 88 | 89 | points[:, 0] += jitters_x 90 | points[:, 1] += jitters_y 91 | points[:, 2] += jitters_z 92 | 93 | lidar_save_path = os.path.join(dst_folder, lidar_path) 94 | label_save_path = os.path.join(dst_folder, label_path ) 95 | 96 | points.astype(np.float32).tofile(lidar_save_path) 97 | 98 | sem_label = sem_label.reshape(-1,1) 99 | sem_label.astype(np.uint8).tofile(label_save_path) 100 | 101 | n = len(all_files) 102 | 103 | with mp.Pool(args.n_cpus) as pool: 104 | 105 | l = list(tqdm(pool.imap(_map, range(n)), total=n)) -------------------------------------------------------------------------------- /create/LiDAR/motion_blur/motion_blur.sh: -------------------------------------------------------------------------------- 1 | CUDA_VISIBLE_DEVICES=0 python gen_motion_blur.py \ 2 | --root_folder ./data_root/nuScenes \ 3 | --dst_folder ./save_root/motion_blur/light \ 4 | --trans_std 0.2 -------------------------------------------------------------------------------- /create/README.md: -------------------------------------------------------------------------------- 1 | # Validation 2 | 3 | ### Outline 4 | - [Study 1: Pixel Distribution](#study-1-pixel-distribution) 5 | - [Study 2: Robust Fine-Tuning](#study-2-robust-fine-tuning) 6 | 7 | 8 | ## Study 1: Pixel Distribution 9 | **Goal:** Assuming that a corruption simulation is realistic enough to reflect real-world situations, the distribution of a corrupted "clean" set should be similar to that of the real-world corruption set. 10 | 11 | **Approach:** We validate this using [ACDC](https://acdc.vision.ee.ethz.ch/news) \[R1\], [nuScenes](https://www.nuscenes.org/nuscenes) \[R2\], [Cityscapes](https://www.cityscapes-dataset.com/) \[R3\], and [Foggy-Cityscapes](https://people.ee.ethz.ch/~csakarid/SFSU_synthetic/) \[R4\], since these datasets contain: 12 | 1. real-world corruption data; 13 | 2. clean data collected by the same sensor types from the same physical locations. 14 | 15 | We simulate corruptions using "clean" images and compare the distribution patterns with their corresponding real-world corrupted data. We do this to ensure that there is no extra distribution shift from aspects like sensor difference (e.g. FOVs and resolutions) and location discrepancy (e.g. environmental and semantic changes). 16 | 17 | | **Real Dark (ACDC-Night)** | **Real Snow (ACDC-Snow)** | **Real Dark (nuScenes-Night)** | **Real Fog (Foggy-Cityscapes)** | 18 | | :-: | :-: | :-: | :-: | 19 | | | | | | 20 | | Synthetic Dark (Level 1) | Synthetic Snow (Level 1) | Synthetic Dark (Level 1) | Synthetic Fog (Level 1) | 21 | | | | | | 22 | | Synthetic Dark (Level 2) | Synthetic Snow (Level 2) | Synthetic Dark (Level 2) | Synthetic Fog (Level 2) | 23 | | | | | | 24 | | Synthetic Dark (Level 3) | Synthetic Snow (Level 3) | Synthetic Dark (Level 3) | Synthetic Fog (Level 3) | 25 | | | | | | 26 | | Synthetic Dark (Level 4) | Synthetic Snow (Level 4) | Synthetic Dark (Level 4) | Synthetic Fog (Level 4) | 27 | | | | | | 28 | | Synthetic Dark (Level 5) | Synthetic Snow (Level 5) | Synthetic Dark (Level 5) | Synthetic Fog (Level 5) | 29 | | | | | | 30 | 31 | **References:** 32 | - \[R1\] C. Sakaridis, D. Dai, and L. V. Gool. "ACDC: The adverse conditions dataset with correspondences for semantic driving scene understanding." ICCV, 2021. 33 | - \[R2\] C., Holger, V. Bankiti, A. H. Lang, S. Vora, V. E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, and O. Beijbom. "nuScenes: A multimodal dataset for autonomous driving." CVPR, 2020. 34 | - \[R3\] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele. "The CityScapes dataset for semantic urban scene understanding." CVPR, 2016. 35 | - \[R4\] C. Sakaridis, D. Dai, and L. V. Gool. “Semantic foggy scene understanding with synthetic data.” IJCV, 2018. 36 | 37 | 38 | ## Study 2: Robust Fine-Tuning 39 | 40 | **Goal:** Assuming that a corruption simulation is realistic enough to reflect real-world situations, a corruption-augmented model should achieve better generalizability than the "clean" model when tested on real-world corruption datasets. 41 | 42 | **Approach:** We validate this using [nuScenes](https://www.nuscenes.org/nuscenes), [nuScenes-Night](https://www.nuscenes.org/nuscenes), and [Foggy-Cityscapes](https://people.ee.ethz.ch/~csakarid/SFSU_synthetic/). We adopt [MonoDepth2](https://github.com/nianticlabs/monodepth2) as the baseline, which is trained on [KITTI](https://www.cvlibs.net/datasets/kitti/raw_data.php) and fine-tuned with corruptions with a small learning rate. We also test training with corruptions from scratch and find the performance is similar to fine-tuning. 43 | 44 | ### nuScenes 45 | | Train | Backbone | Resolution | CorruptAug | Abs Rel | Sq Rel | RMSE | RMSE log | a1 | a2 | a3 | 46 | |:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:| 47 | | KITTI | ResNet-18 | 640x192 | No | 0.304 | 3.472 | 9.068 | 0.409 | 0.563 | 0.794 | 0.890 | 48 | | KITTI | ResNet-18 | 640x192 | Yes | 0.297 | 2.991 | 8.790 | 0.405 | 0.558 | 0.794 | 0.893 | 49 | | KITTI | ResNet-50 | 640x192 | No | 0.302 | 3.219 | 9.054 | 0.416 | 0.555 | 0.786 | 0.886 | 50 | | KITTI | ResNet-50 | 640x192 | Yes | 0.294 | 2.947 | 8.754 | 0.404 | 0.565 | 0.795 | 0.892 | 51 | 52 | ### nuScenes-Night 53 | | Train | Backbone | Resolution | CorruptAug | Abs Rel | Sq Rel | RMSE | RMSE log | a1 | a2 | a3 | 54 | |:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:| 55 | | KITTI | ResNet-18 | 640x192 | No | 0.397 | 3.408 | 8.700 | 0.513 | 0.387 | 0.659 | 0.822 | 56 | | KITTI | ResNet-18 | 640x192 | Yes | 0.362 | 3.149 | 8.391 | 0.477 | 0.434 | 0.714 | 0.852 | 57 | | KITTI | ResNet-50 | 640x192 | No | 0.418 | 3.599 | 8.928 | 0.539 | 0.363 | 0.626 | 0.802 | 58 | | KITTI | ResNet-50 | 640x192 | Yes | 0.357 | 3.128 | 8.168 | 0.462 | 0.444 | 0.723 | 0.861 | 59 | 60 | ### Foggy-Cityscapes 61 | | Train | Backbone | Resolution | CorruptAug | Abs Rel | Sq Rel | RMSE | RMSE log | a1 | a2 | a3 | 62 | |:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:| 63 | | KITTI | ResNet-18 | 416x128 | No | 0.421 | 7.057 | 15.207 | 0.527 | 0.360 | 0.636 | 0.806 | 64 | | KITTI | ResNet-18 | 416x128 | Yes | 0.385 | 6.310 | 14.654 | 0.489 | 0.399 | 0.682 | 0.836 | 65 | | KITTI | ResNet-18 | 512x256 | No | 0.364 | 6.371 | 14.690 | 0.483 | 0.440 | 0.703 | 0.838 | 66 | | KITTI | ResNet-18 | 512x256 | Yes | 0.349 | 5.645 | 14.723 | 0.488 | 0.434 | 0.698 | 0.834 | 67 | 68 | 69 | 70 | 71 | -------------------------------------------------------------------------------- /docs/GIFs/camera/brightness-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/brightness-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/brightness-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/brightness-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/brightness-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/brightness-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/camera-crash-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/camera-crash-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/camera-crash-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/camera-crash-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/camera-crash-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/camera-crash-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/clean.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/clean.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/color-quant-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/color-quant-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/color-quant-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/color-quant-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/color-quant-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/color-quant-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/fog-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/fog-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/fog-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/fog-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/fog-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/fog-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/frame-lost-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/frame-lost-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/frame-lost-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/frame-lost-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/frame-lost-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/frame-lost-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/low-light-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/low-light-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/low-light-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/low-light-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/low-light-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/low-light-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/motion-blur-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/motion-blur-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/motion-blur-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/motion-blur-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/motion-blur-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/motion-blur-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/snow-easy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/snow-easy.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/snow-hard.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/snow-hard.gif -------------------------------------------------------------------------------- /docs/GIFs/camera/snow-mid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/camera/snow-mid.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/beam_missing-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/beam_missing-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/beam_missing-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/beam_missing-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/beam_missing-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/beam_missing-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/clean.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/clean.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/cross_sensor-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/cross_sensor-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/cross_sensor-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/cross_sensor-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/cross_sensor-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/cross_sensor-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/crosstalk-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/crosstalk-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/crosstalk-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/crosstalk-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/crosstalk-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/crosstalk-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/fog-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/fog-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/fog-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/fog-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/fog-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/fog-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/incomplete_echo-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/incomplete_echo-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/incomplete_echo-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/incomplete_echo-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/incomplete_echo-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/incomplete_echo-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/motion_blur-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/motion_blur-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/motion_blur-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/motion_blur-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/motion_blur-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/motion_blur-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/snow-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/snow-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/snow-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/snow-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/snow-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/snow-moderate.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/wet_ground-heavy.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/wet_ground-heavy.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/wet_ground-light.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/wet_ground-light.gif -------------------------------------------------------------------------------- /docs/GIFs/lidar/wet_ground-moderate.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/GIFs/lidar/wet_ground-moderate.gif -------------------------------------------------------------------------------- /docs/images/benchmark.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/benchmark.png -------------------------------------------------------------------------------- /docs/images/definition.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/definition.png -------------------------------------------------------------------------------- /docs/images/levels.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/levels.png -------------------------------------------------------------------------------- /docs/images/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/logo.png -------------------------------------------------------------------------------- /docs/images/maptr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/maptr.png -------------------------------------------------------------------------------- /docs/images/metrics_Fusion.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/metrics_Fusion.png -------------------------------------------------------------------------------- /docs/images/metrics_LiDAR.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/metrics_LiDAR.png -------------------------------------------------------------------------------- /docs/images/metrics_camera.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/metrics_camera.png -------------------------------------------------------------------------------- /docs/images/qua.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/qua.png -------------------------------------------------------------------------------- /docs/images/robustness.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/robustness.png -------------------------------------------------------------------------------- /docs/images/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mapbench/toolkit/ec6a6f916d255570fd73c0f07b2da3a2eee7c228/docs/images/teaser.png --------------------------------------------------------------------------------