└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # 3d detection papers 2 | 3 | > Author: Li Heyuan (李贺元)
4 | > Email: lhyfst@gmail.com
5 | > The papers in this list are about Autonomous Vehicles 3d detection & semantic segmentation
6 | > especially those using point clouds and in deep learning methods.
7 | > All rights reserved 8 | 9 | 10 | If you have any suggestion or want to recommend new papers, please feel free to let me know.
11 | I have read most of the papers here, and am very happy to discuss with you if you have any issues on these papers.
12 | I will keep updating this project continuously.
13 | 14 | --- 15 | 16 | I will improve this project in a few days.
17 | 18 | todo list: 19 | 1. links -- done 20 | 2. recommended papers -- done. The ones that I particularly liked are marked with :star:. 21 | 3. authors -- done 22 | 4. models -- remove this item 23 | 5. relevant code -- done 24 | 6. rank by year -- done 25 | 7. active researchers -- done 26 | 8. write a brief review for each mainstream method 27 | 9. try to write some reviews for the recommended papers, if I have time. 28 | 29 | 30 | ## Mainstream Method Series 31 | - Voxel 32 | - Multi-view 33 | - Pointnet 34 | - Other 35 | 36 | ## Voxel 37 | - [Sliding shapes for 3d object detection in depth images](http://slidingshapes.cs.princeton.edu/paper.pdf), 38 | Shuran Song, Jianxiong Xiao, 39 | [code](http://slidingshapes.cs.princeton.edu/), 40 | [website](http://slidingshapes.cs.princeton.edu/), 41 | ECCV, 2014 42 | - [Voxnet: A 3d convolutional neural network for real-time object recognition](https://www.ri.cmu.edu/pub_files/2015/9/voxnet_maturana_scherer_iros15.pdf), 43 | Daniel Maturana and Sebastian Scherer, 44 | [code](https://github.com/dimatura/voxnet), 45 | [website](http://dimatura.net/research/voxnet/), 46 | IROS, 2015 47 | - [Deep sliding shapes for amodal 3d object detection in rgb-d images](http://dss.cs.princeton.edu/paper.pdf), 48 | Shuran Song, Jianxiong Xiao, 49 | [code](https://github.com/shurans/DeepSlidingShape), 50 | [website](http://dss.cs.princeton.edu/), 51 | CVPR, 2016 52 | - [Octnet: Learning deep 3d representations at high resolutions](https://arxiv.org/pdf/1611.05009.pdf), 53 | Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger, 54 | [code](https://github.com/griegler/octnet), 55 | CVPR, 2017 :star: 56 | - [3d fully convolutional network for vehicle detection in point cloud](https://arxiv.org/pdf/1611.08069.pdf), 57 | Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger, 58 | [unofficial code](https://github.com/yukitsuji/3D_CNN_tensorflow), 59 | IROS, 2017 60 | - [Voting for voting in online point cloud object detection](http://www.robots.ox.ac.uk/~mobile/Papers/2015RSS_wang.pdf), 61 | Dominic Zeng Wang, Ingmar Posner, 62 | Robotics: Science and System, 2015 63 | - [Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks](https://arxiv.org/pdf/1609.06666), 64 | Martin Engelcke, Dushyant Rao, Dominic Zeng Wang, Chi Hay Tong, Ingmar Posner, 65 | ICRA, 2017 66 | 67 | 68 | ## Multi-view 69 | - [Pedestrian detection combining RGB and dense LIDAR data](https://ieeexplore.ieee.org/document/6943141), 70 | Cristiano Premebida, João Carreira, Jorge Batista, Urbano Nunes, 71 | IROS, 2014 72 | - [3d-assisted feature synthesis for novel views of an object](http://openaccess.thecvf.com/content_iccv_2015/papers/Su_3D-Assisted_Feature_Synthesis_ICCV_2015_paper.pdf), 73 | Hao Su, Fan Wang, Eric Yi, Leonidas Guibas, 74 | ICCV, 2015 75 | - [Multiview random forest of local experts combining rgb and lidar data for pedestrian detection](https://ieeexplore.ieee.org/document/7225711), 76 | A. González, G. Villalonga, J. Xu, D. Vázquez, J. Amores, and A. López., 77 | IEEE Intelligent Vehicles Symposium, 2015 78 | - [Multiview convolutional neural networks for 3d shape recognition](http://vis-www.cs.umass.edu/mvcnn/docs/su15mvcnn.pdf), 79 | Hang Su Subhransu Maji Evangelos Kalogerakis Erik Learned-Miller, 80 | [code](https://github.com/jongchyisu/mvcnn_pytorch) 81 | ICCV, 2015 82 | - [Vehicle detection from 3d lidar using fully convolutional network](https://arxiv.org/pdf/1608.07916.pdf), 83 | Bo Li, Tianlei Zhang, Tian Xia, 84 | Robotics: Science and System, 2016 85 | - [Volumetric and multi-view cnns for object classification on 3d data](http://openaccess.thecvf.com/content_cvpr_2016/papers/Qi_Volumetric_and_Multi-View_CVPR_2016_paper.pdf), 86 | Charles R. Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, Leonidas J. Guibas, 87 | CVPR, 2016 88 | - [Fusionnet: 3d object classification using multiple data representations](https://arxiv.org/pdf/1607.05695.pdf), 89 | Vishakh Hegde, Reza Zadeh, 90 | CoRR, 2016 91 | - [Multi-view 3d object detection network for autonomous driving](https://arxiv.org/pdf/1611.07759.pdf), 92 | Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia, 93 | [code](https://github.com/bostondiditeam/MV3D), 94 | CVPR, 2017 :star: 95 | - [Joint 3d proposal generation and object detection from view aggregation](https://arxiv.org/pdf/1712.02294.pdf), 96 | Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, Steven L. Waslander, 97 | [code](https://github.com/kujason/avod), 98 | IROS, 2018 99 | - [Pixor: Real-time 3d object detection from point clouds](https://arxiv.org/pdf/1902.06326), 100 | Bin Yang, Wenjie Luo, Raquel Urtasun, 101 | CVPR, 2018 :star: 102 | - [Deep continuous fusion for multi-sensor 3d object detection](http://openaccess.thecvf.com/content_ECCV_2018/papers/Ming_Liang_Deep_Continuous_Fusion_ECCV_2018_paper.pdf), 103 | Ming Liang, Bin Yang, Shenlong Wang, and Raquel Urtasun, 104 | ECCV, 2018 :star: 105 | - [MLOD: A multi-view 3D object detection based on robust feature fusion method](https://arxiv.org/pdf/1909.04163.pdf) 106 | Jian Deng and Krzysztof Czarnecki, 107 | 2019 108 | 109 | ## PointNet 110 | - [Pointnet: Deep learning on point sets for 3d classification and segmentation](https://arxiv.org/abs/1612.00593), 111 | Charles R. Qi*, Hao Su*, Kaichun Mo, Leonidas J. Guibas, 112 | [code](https://github.com/charlesq34/pointnet), 113 | [website](http://stanford.edu/~rqi/pointnet/), 114 | CVPR, 2017 :star: 115 | - [Pointnet++: Deep hierarchical feature learning on point sets in a metric space](https://arxiv.org/abs/1706.02413), 116 | Charles R. Qi, Li (Eric) Yi, Hao Su, Leonidas J. Guibas, 117 | [code](https://github.com/charlesq34/pointnet2), 118 | [website](http://stanford.edu/~rqi/pointnet2/), 119 | NIPS, 2017 120 | - [Frustum pointnets for 3d object detection from rgb-d data](https://arxiv.org/abs/1711.08488), 121 | Charles R. Qi, Wei Liu, Chenxia Wu, Hao Su, Leonidas J. Guibas, 122 | [code](https://github.com/charlesq34/frustum-pointnets), 123 | [website](http://stanford.edu/~rqi/frustum-pointnets/), 124 | CVPR, 2018 :star: 125 | - [PointRCNN 3D Object Proposal Generation and Detection from Point Cloud](https://arxiv.org/pdf/1812.04244.pdf), 126 | Shaoshuai Shi, Xiaogang Wang, Hongsheng Li, 127 | 2018 :star: 128 | - [Pointfusion: Deep sensor fusion for 3d bounding box estimation](https://arxiv.org/pdf/1711.10871.pdf), 129 | Danfei Xu, Dragomir Anguelov, Ashesh Jain, 130 | CVPR, 2018 131 | - [Voxelnet: End-to-end learning for point cloud based 3d object detection](https://arxiv.org/pdf/1711.06396.pdf), 132 | Yin Zhou, Oncel Tuzel, 133 | [unofficial code](https://github.com/jeasinema/VoxelNet-tensorflow), 134 | CVPR, 2018 :star: 135 | - [Second: Sparsely embedded convolutional detection](https://pdfs.semanticscholar.org/5125/a16039cabc6320c908a4764f32596e018ad3.pdf), 136 | Yan Yan,, Yuxing Mao, and Bo Li, 137 | [code](https://github.com/traveller59/second.pytorch), 138 | Sensors, 2018 139 | - [Pointpillars: Encoders for object detection from point clouds](https://arxiv.org/pdf/1812.05784.pdf), 140 | Alex H. Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang, Oscar Beijbom, 141 | [code](https://github.com/nutonomy/second.pytorch), 142 | 2018 143 | - [RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement](https://arxiv.org/pdf/1811.03818), 144 | Kiwoo Shin, Youngwook Paul Kwon, Masayoshi Tomizuka, 145 | [code](https://github.com/Kiwoo/RoarNet), 146 | 2018 :star: 147 | - [IPOD: Intensive Point-based Object Detector for Point Cloud](https://arxiv.org/pdf/1812.05276.pdf), 148 | Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia, 149 | 2018 150 | - [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://arxiv.org/pdf/1903.01864.pdf), 151 | Zhixin Wang, Kui Jia, 152 | 2019 :star: 153 | - [3D Object Detection Using Scale Invariant and Feature Reweighting Networks](https://arxiv.org/pdf/1711.10871.pdf), 154 | Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang, 155 | AAAI, 2019 156 | - [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://arxiv.org/pdf/1907.10471.pdf)Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia, 157 | ICCV, 2019 :star: 158 | - [Patch Refinement - Localized 3D Object Detection](https://arxiv.org/pdf/1910.04093.pdf) 159 | Johannes Lehner, Andreas Mitterecker, Thomas Adler, Markus Hofmarcher, Bernhard Nessler, Sepp Hochreiter, 160 | 2019 161 | 162 | ## Other 163 | - [Recurrent slice networks for 3d segmentation of point clouds](https://arxiv.org/pdf/1802.04402.pdf), 164 | Qiangui Huang, Weiyue Wang, Ulrich Neumann, 165 | [code](https://github.com/qianguih/RSNet), 166 | CVPR, 2018 :star: 167 | - [Pointsift: A sift-like network module for 3d point cloud semantic segmentation](https://arxiv.org/abs/1807.00652), 168 | Mingyang Jiang, Yiran Wu, Tianqi Zhao, Zelin Zhao, Cewu Lu, 169 | [code](https://github.com/MVIG-SJTU/pointSIFT), 170 | CoRR, 2018 171 | - [A General Pipeline for 3D Detection of Vehicles](https://ieeexplore.ieee.org/abstract/document/8461232) 172 | Xinxin Du ; Marcelo H. Ang ; Sertac Karaman ; Daniela Rus, 173 | 2018 174 | - [Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud](https://arxiv.org/pdf/1907.03670.pdf),Shaoshuai Shi, Zhe Wang, Xiaogang Wang, Hongsheng Li, 175 | 2019 :star: 176 | - [Multi-Task Multi-Sensor Fusion for 3D Object Detection](http://openaccess.thecvf.com/content_CVPR_2019/papers/Liang_Multi-Task_Multi-Sensor_Fusion_for_3D_Object_Detection_CVPR_2019_paper.pdf), 177 | Ming Liang, Bin Yang, Yun Chen, Rui Hu, Raquel Urtasun, 178 | 2019, :star: 179 | - [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://arxiv.org/pdf/1902.09630.pdf), 180 | Hamid Rezatofighi, Nathan Tsoi1, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese, 181 | 2019, :star: 182 | - [Voxel-FPN: multi-scale voxel feature aggregationin 3D object detection from point clouds](https://arxiv.org/ftp/arxiv/papers/1907/1907.05286.pdf), 183 | Bei Wang, Jianping An and Jiayan Cao, 184 | 2019, :star: 185 | - [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](http://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_PointRCNN_3D_Object_Proposal_Generation_and_Detection_From_Point_Cloud_CVPR_2019_paper.pdf), 186 | Shaoshuai Shi, Xiaogang Wang, Hongsheng Li, 187 | 2019 188 | - [Fast Point R-CNN](https://arxiv.org/pdf/1908.02990.pdf), 189 | Yilun Chen, Shu Liu, Xiaoyong Shen, Jiaya Jia, 190 | 2019 191 | - [Three-dimensional Backbone Network for 3D Object Detection in Traffic Scenes](https://arxiv.org/pdf/1901.08373.pdf) 192 | Xuesong Li, Jose Guivant, Ngaiming Kwok, Yongzhi Xu, Ruowei Li, Hongkun Wu, 193 | 2019 194 | - [SCNet: Subdivision Coding Network for Object Detection Based on 3D Point Cloud](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8813061) 195 | ZHIYU WANG, HAO FU, LI WANG, LIANG XIAO, AND BIN DA, 196 | 2019 197 | - [PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module](https://arxiv.org/pdf/1911.06084.pdf) 198 | Liang Xie, Chao Xiang, Zhengxu Yu, Guodong Xu, Zheng Yang, Deng Cai1, Xiaofei He, 199 | AAAI, 2019 200 | - [HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection] 201 | (https://arxiv.org/pdf/2003.00186.pdf) 202 | Maosheng Ye, Shuangjie Xu, Tongyi Cao, 203 | CVPR, 2020 204 | - [FPConv: Learning Local Flattening for Point Convolution] 205 | (https://arxiv.org/pdf/2002.10701.pdf) 206 | Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han, 207 | CVPR, 2020 208 | - [Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection] 209 | (https://arxiv.org/pdf/2002.10701.pdf) 210 | Liang Du, Xiaoqing Ye, Xiao Tan, Jianfeng Feng, Zhenbo Xu, Errui Ding and Shilei Wen, 211 | CVPR, 2020 212 | - [SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds] 213 | (https://arxiv.org/pdf/2006.04043.pdf) 214 | Qingdong He, Zhengning Wang, Hao Zeng, Yi Zeng, Shuaicheng Liu, Bing Zeng, 215 | CVPR, 2020 216 | - [H3DNet: 3D Object Detection Using Hybrid Geometric Primitives] 217 | (https://arxiv.org/pdf/2006.05682.pdf) 218 | Zaiwei Zhang, Bo Sun, Haitao Yang, Qixing Huang 219 | --------------------------------------------------------------------------------