├── .gitignore ├── LICENSE ├── README.md ├── _config.yml ├── _includes └── head-custom-google-analytics.html ├── _layouts └── default.html ├── assets └── css │ └── style.scss ├── banner.png ├── barbershop_pano.webp ├── garden_pano.webp ├── generate_NERF_transforms.py ├── lone_monk_pano.webp ├── nerf_barbershop_spherical.gif ├── nerf_garden.gif ├── nerf_lone_monk.gif ├── sha256sums.txt └── thumbnails ├── page-1.png ├── page-2.png ├── page-3.png ├── page-4.png ├── page-5.png └── page-6.png /.gitignore: -------------------------------------------------------------------------------- 1 | *.exr 2 | *.mp4 3 | 4 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA. 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |

2 | 3 |

5 |

6 |

7 |

8 |

9 | 10 | 11 | # [SILVR: A Synthetic Immersive Large-Volume Plenoptic Dataset](https://idlabmedia.github.io/large-lightfields-dataset) 12 |

13 | 14 | [![GitHub stars](https://img.shields.io/github/stars/IDLabMedia/large-lightfields-dataset)](https://github.com/IDLabMedia/large-lightfields-dataset/stargazers) [![Papers With Code](https://img.shields.io/static/v1?label=Papers%20With%20Code&message=Dataset&color=09b)](https://paperswithcode.com/dataset/silvr) [![Papers With Code](https://img.shields.io/static/v1?label=Papers%20With%20Code&message=Paper&color=09b)](https://cs.paperswithcode.com/paper/silvr-a-synthetic-immersive-large-volume) [![arXiv](https://img.shields.io/static/v1?label=ariXiv&message=SILVR&color=brightgreen)](https://arxiv.org/abs/2204.09523) [![BibTeX](https://img.shields.io/static/v1?label=Cite&message=BibTeX&color=a26)](#credits) 15 | 16 | We present _SILVR_, a dataset of light field images for six-degrees-of-freedom 17 | navigation in large fully-immersive volumes. The _SILVR_ dataset is short for 18 | _"**S**ynthetic **I**mmersive **L**arge-**V**olume **R**ay"_ dataset. 19 | 20 | ## Properties 21 | Our dataset exhibits the following properties: 22 | 23 | - **synthetic**: Rendered using Blender 3.0 with Cycles, the images are 24 | perfect and do not need any calibration. Camera positions and lens 25 | configurations are known exactly and provided in the corresponding JSON 26 | files. 27 | - **large interpolation volume**: The camera configurations span a 28 | relatively large volume (a couple of meters in diameter). 29 | - **large field of view**: In order to maximize the _interpolation volume_ 30 | (a.k.a: the walkable volume of light), the images are rendered using fisheye 31 | lenses with a field of view of 180°. 32 | - **immersive**: Thanks to the large field of view and positioning of the 33 | viewpoints, every point within the interpolation volume has a full panoramic 34 | field of view of light information available. 35 | - **realism**: The selected scenes have reasonable realism. 36 | - **depth maps**: As the images are computer-generated renders, we provide 37 | depth maps for every image. 38 | - **specularities** and **reflections**: The scenes exhibit some specularities 39 | or reflections, including mirrors. Reflections and mirrors always have the 40 | depth of the surface, and not the apparent depth of the reflections. 41 | - **volumetrics**: Some volumetrics are also present (fire, smoke, fog) in the 42 | `garden` scene. 43 | - **densly rendered**: The camera setup is rather dense (around 10cm spacing 44 | between cameras). 45 | 46 | ## Scenes 47 | 48 | We present light field renders with various camera setup configurations for three scenes: _Agent 327: Barbershop_, _Zen Garden_, and _Lone Monk_. 49 | 50 | ### Agent 327: Barbershop 51 | 52 | ![Barbershop Panorama](./barbershop_pano.webp) 53 | 54 | This scene is taken from [the Blender website, under the "demo files" 55 | section](https://www.blender.org/download/demo-files/#cycles). It is licensed 56 | CC-BY, by [Blender Foundation](https://studio.blender.org). 57 | 58 | Download the original _Agent 327: Barbershop_ scene **with light field camera setups** [here (272MB)](https://cloud.ilabt.imec.be/index.php/s/anFWqc5TwW646Ex). 59 | Note that our [Blender Lightfield Addon](https://github.com/IDLabMEDIA/blender-lightfield-addon) is required to open the Blender file with light fields. 60 | 61 | ### Zen Garden 62 | 63 | ![Zen Garden Panorama](./garden_pano.webp) 64 | 65 | This scene is made in-house by IDLab-MEDIA. It is licensed [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/). 66 | 67 | Download the _Zen Garden_ scene **with light field camera setups** [here (231MB)](https://cloud.ilabt.imec.be/index.php/s/Moqz2e7mNs2AFcT). 68 | Note that our [Blender Lightfield Addon](https://github.com/IDLabMEDIA/blender-lightfield-addon) is required to open the Blender file with light fields. 69 | 70 | ### Lone Monk 71 | 72 | ![Lone Monk Panorama](./lone_monk_pano.webp) 73 | 74 | This scene is made by Carlo Bergonzini from [Monorender](http://www.monorender.com/), licensed CC-BY. 75 | The original scene is also available for download from [the Blender website, under the "demo files" 76 | section](https://www.blender.org/download/demo-files/#cycles). 77 | Applied modifications: 78 | - Added roof geometry above the section with the chair. 79 | - Solidify modifier on the roof tiles. 80 | 81 | Download the modified _Lone Monk_ scene **with light field camera setups** [here (33MB)](https://cloud.ilabt.imec.be/index.php/s/wTwwPyD8pp4CQkp). 82 | Note that our [Blender Lightfield Addon](https://github.com/IDLabMEDIA/blender-lightfield-addon) is required to open the Blender file with light fields. 83 | 84 | ## Download 85 | 86 | All images are provided in OpenEXR format with HDR colors and depth in meters. 87 | Files are available for download from our own [storage service](https://cloud.ilabt.imec.be/index.php/s/KHWopdXmT3Dxo5P). 88 | All files can be downloaded individually. Below you can find an overview of the different files and their sizes. 89 | 90 | ``` 91 | - Barbershop 92 | - barbershop_LFCuboid_1mx3mx1m.tar (16 GB) 93 | - barbershop_LFSphere_e105cm_d145cm.tar ( 7.5 GB) 94 | - barbershop_LFSphere_e110cm_d100cm.tar ( 43MB) 95 | - barbershop_LFCuboid_8panos.tar ( 172MB) 96 | - Garden 97 | - garden_LFCuboid_2x2x1.tar (25 GB) 98 | - garden_LFSphere_e100cm_d170cm.tar ( 8.7 GB) 99 | - garden_LFSphere_e100cm_d50cm.tar ( 51MB) 100 | - garden_LFCuboid_8panos.tar ( 86MB) 101 | - Lone Monk 102 | - lone_monk_LFCuboid_4mx4mx3m.tar (24 GB) 103 | - lone_monk_LFSphere_e220cm_d400cm.tar ( 6.8 GB) 104 | - lone_monk_LFSphere_e160cm_d220cm.tar ( 500MB) 105 | - lone_monk_LFCuboid_8panos.tar ( 159MB) 106 | ``` 107 | 108 | Find the sha256 checksums [here](./sha256sums.txt). 109 | The letters `e` and `d` in the filenames are for 'elevation' and 'diameter'. 110 | 111 | **Update 2022-09-07**: Reuploaded `garden_LFCuboid_2x2x1.tar` after fixing issue #3. 112 | **Update 2022-09-07**: Reuploaded `garden_mmsys2022.blend` after fixing issue #4. 113 | 114 | ## Tools 115 | 116 | ### Lens Reproject 117 | As the images are rendered using equisolid fish-eye lenses, we also supply a 118 | tool (written in C++) to generate reprojected images with other lens types, as 119 | most established light field research assumes rectilinear lenses. 120 | 121 | **Project page:** [github.com/IDLabMEDIA/image-lens-reproject](https://github.com/IDLabMEDIA/image-lens-reproject) 122 | 123 | ### NeRF configuration generator 124 | We provide a Python script 125 | [`generate_NERF_transforms.py`](https://github.com/IDLabMEDIA/large-lightfield-dataset/blob/main/generate_NERF_transforms.py) 126 | that produces the required NeRF configuration to test our scenes in NeRF using 127 | [instant-ngp](https://github.com/NVlabs/instant-ngp). 128 | 129 | **Script source:** [github.com/IDLabMEDIA/large-lightfield-dataset/generate_NERF_transforms.py](https://github.com/IDLabMEDIA/large-lightfield-dataset/blob/main/generate_NERF_transforms.py) 130 | 131 | Example on the spherical rendering configuration of _barbershop_, _lone monk_ 132 | and _garden_, after reprojecting it using the `lens-reproject` tool (as 133 | instant-ngp only support rectilinear images): 134 | 135 | NeRF Barbershop

136 | 137 | #### NeRF: How to? 138 | First, we reproject the images (in this example from the scene _lone monk_) 139 | with a rectilinear lens of 18mm focal length on a 36mm sensor, and store them 140 | in PNG format with a resolution 1/8th of the original images (i.e.: 256x256), 141 | while reducing exposure by one stop and applying Reinhard tone mapping with 142 | maximum brightness 5: 143 | ```sh 144 | mkdir lone_monk_perspective 145 | ./reproject --parallel 4 --rectilinear 18,36 --scale 0.125 \ 146 | --png --exposure -1 --reinhard 5 \ 147 | --input-dir lone_monk/LFSphere_e220cm_d400cm/exr \ 148 | --input-cfg lone_monk/LFSphere_e220cm_d400cm/lightfield.json \ 149 | --output-dir lone_monk_perspective \ 150 | --output-cfg lone_monk_perspective/lightfield.json 151 | ``` 152 | Now, we generate the `transforms.json` required by instant-ngp: 153 | ```sh 154 | python3 generate_NERF_transforms.py \ 155 | --scene lone_monk \ 156 | --dataset-config lone_monk_perspective/lightfield.json \ 157 | --output-transforms lone_monk_perspective/transforms.json 158 | ``` 159 | Finally, open the dataset with with instant-ngp: 160 | ```sh 161 | cd instant-ngp 162 | build/testbed --scene=path/to/lone_monk_perspective/transforms.json 163 | ``` 164 | Here, make sure to set the _"Near distance"_ under the _Training_ options to 0. 165 | Consider restarting training after you did. 166 | 167 | ### Blender Lightfield Addon 168 | [The Blender addon](https://github.com/IDLabMEDIA/blender-lightfield-addon) we 169 | developed in-house to produce the dataset images is also open-sourced to enable 170 | anyone to start producing light field datasets from virtual scenes in Blender. 171 | 172 | **Project page:** [github.com/IDLabMEDIA/blender-lightfield-addon](https://github.com/IDLabMEDIA/blender-lightfield-addon) 173 | 174 |

175 | 176 | ![Addon GIF](https://github.com/IDLabMedia/blender-lightfield-addon/raw/main/docs/settings.gif) 177 | 178 | ## Credits 179 | 180 | To cite this paper: 181 | 182 | 183 | ```bibtex 184 | @inproceedings{courteaux2022silvr, 185 | title = {{SILVR: A Synthetic Immersive Large-Volume Plenoptic Dataset}}, 186 | author = {Courteaux, Martijn and Artois, Julie and De Pauw, Stijn and Lambert, Peter and Van Wallendael, Glenn}, 187 | year = {2022}, 188 | doi = {10.1145/3524273.3532890}, 189 | publisher = {Association for Computing Machinery}, 190 | url = {https://doi.org/10.1145/3524273.3532890}, 191 | address = {New York, NY, USA}, 192 | month = {jun}, 193 | numpages = {6}, 194 | isbn = {978-1-4503-9283-9/22/06}, 195 | booktitle = {13th ACM Multimedia Systems Conference (MMSys '22)}, 196 | location = {Athlone, Ireland} 197 | } 198 | ``` 199 | 200 | 201 | Dataset and paper by [IDLab MEDIA](https://media.idlab.ugent.be/). 202 | -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- 1 | title: SILVR 2 | theme: jekyll-theme-cayman 3 | google_analytics: G-1BENQR5CTV 4 | -------------------------------------------------------------------------------- /_includes/head-custom-google-analytics.html: -------------------------------------------------------------------------------- 1 | {% if site.google_analytics %} 2 | 3 | 10 | {% endif %} 11 | -------------------------------------------------------------------------------- /_layouts/default.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | {% seo %} 6 | 7 | 8 | 9 | 10 | 11 | 12 | {% include head-custom.html %} 13 | 14 | 15 | 16 | 17 | 36 | 37 |

38 | {{ content }} 39 | 40 | 46 |

47 | 48 | 49 | -------------------------------------------------------------------------------- /assets/css/style.scss: -------------------------------------------------------------------------------- 1 | --- 2 | --- 3 | 4 | @import "{{ site.theme }}"; 5 | 6 | div.thumbnails a { 7 | text-decoration: none; 8 | } 9 | div.thumbnails img { 10 | max-width: 340px; 11 | width: 10%; 12 | } 13 | div.thumbnails.in-body { 14 | display: none; 15 | } 16 | -------------------------------------------------------------------------------- /banner.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/banner.png -------------------------------------------------------------------------------- /barbershop_pano.webp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/barbershop_pano.webp -------------------------------------------------------------------------------- /garden_pano.webp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/garden_pano.webp -------------------------------------------------------------------------------- /generate_NERF_transforms.py: -------------------------------------------------------------------------------- 1 | import os 2 | import math 3 | import numpy as np 4 | import json 5 | import argparse 6 | 7 | parser = argparse.ArgumentParser() 8 | 9 | parser.add_argument("--dataset-config", type=str, required=True, help="dataset config file (i.e.: the 'lightfield.cfg' file).") 10 | parser.add_argument("--subdir", type=str, required=False, help="path prefix to include in the filename paths") 11 | parser.add_argument("--output-transforms", type=str, required=True, help="path to the transforms.json to produce.") 12 | parser.add_argument("--scene", type=str, 13 | choices=["garden", "barbershop", "lone_monk", "kitchen"], 14 | help="A specific scene name that will be used to pick sane scaling/aabb defaults.") 15 | parser.add_argument("--scale", type=float, 16 | help="A scale for NeRF to fit the unit cube.") 17 | parser.add_argument("--extra-offset", type=float, nargs=3, 18 | help="A 3-vector that defines extra offset in NeRF coordinates") 19 | parser.add_argument("--render-aabb", type=float, nargs=6, 20 | help="Two 3-vectors that define the AABB min and max in NeRF coordinates") 21 | args = parser.parse_args() 22 | 23 | names = [] 24 | positions = [] # camera positions in 3-tuples 25 | rotations = [] # camera orientations in 3-tuples (degrees) 26 | 27 | if args.dataset_config.endswith(".cfg"): 28 | # Load the stupid format. 29 | with open(args.dataset_config, "r") as file: 30 | def nextline(): 31 | return file.readline().split(",") 32 | file.readline() 33 | resolution = [int(x) for x in nextline()] 34 | proj0 = [float(x) for x in nextline()] 35 | proj1 = [float(x) for x in nextline()] 36 | proj2 = [float(x) for x in nextline()] 37 | proj3 = [float(x) for x in nextline()] 38 | camera_lines = file.readlines() 39 | for cl in camera_lines: 40 | p = cl.split(",") 41 | names.append(p[0]) 42 | positions.append([float(x) for x in p[1:4]]) 43 | rotations.append([float(x) for x in p[4:]]) 44 | 45 | print("proj matrix") 46 | print(proj0) 47 | print(proj1) 48 | print(proj2) 49 | print(proj3) 50 | 51 | camera_angle_x = 2.0 * np.arctan(1.0 / proj0[0]) 52 | camera_angle_y = 2.0 * np.arctan(1.0 / proj1[1]) 53 | elif args.dataset_config.endswith(".json"): 54 | with open(args.dataset_config, "r") as file: 55 | cfg = json.load(file) 56 | cam_type = cfg['camera']['type'] 57 | resolution = cfg['resolution'] 58 | if cam_type == 'PERSP': 59 | proj = cfg['camera']['projection_matrix'] 60 | camera_angle_x = 2.0 * np.arctan(1.0 / proj[0][0]) 61 | camera_angle_y = 2.0 * np.arctan(1.0 / proj[1][1]) 62 | else: 63 | # Not supported by Nerf 64 | raise NotImplementedError("Not supported by NerF") 65 | 66 | for fr in cfg['frames']: 67 | names.append(fr['name']) 68 | positions.append(fr['position']) 69 | rotations.append(fr['rotation']) 70 | else: 71 | parser.print_usage() 72 | print("Not a valid config file given. Either .json (preferred) or .cfg (deprecated)") 73 | exit(1) 74 | 75 | focal = [float(x) for x in resolution] 76 | principal_point = [x * 0.5 for x in focal] 77 | print("camera_angle_x", camera_angle_x, "rad =", camera_angle_x / np.pi * 180, "degrees") 78 | print("camera_angle_y", camera_angle_y, "rad =", camera_angle_y / np.pi * 180, "degrees") 79 | average_position = np.mean(positions, axis=0) 80 | print("average_position", average_position) 81 | 82 | def generate_transform_matrix(pos, rot): 83 | def Rx(theta): 84 | return np.matrix([[ 1, 0 , 0 ], 85 | [ 0, np.cos(theta),-np.sin(theta)], 86 | [ 0, np.sin(theta), np.cos(theta)]]) 87 | def Ry(theta): 88 | return np.matrix([[ np.cos(theta), 0, np.sin(theta)], 89 | [ 0 , 1, 0 ], 90 | [-np.sin(theta), 0, np.cos(theta)]]) 91 | def Rz(theta): 92 | return np.matrix([[ np.cos(theta), -np.sin(theta), 0 ], 93 | [ np.sin(theta), np.cos(theta) , 0 ], 94 | [ 0 , 0 , 1 ]]) 95 | 96 | R = Rz(rot[2]) * Ry(rot[1]) * Rx(rot[0]) 97 | xf_rot = np.eye(4) 98 | xf_rot[:3,:3] = R 99 | 100 | xf_pos = np.eye(4) 101 | xf_pos[:3,3] = pos # - average_position 102 | 103 | # barbershop_mirros_hd_dense: 104 | # - camera plane is y+z plane, meaning: constant x-values 105 | # - cameras look to +x 106 | 107 | # Don't ask me... 108 | extra_xf = np.matrix([ 109 | [-1, 0, 0, 0], 110 | [ 0, 0, 1, 0], 111 | [ 0, 1, 0, 0], 112 | [ 0, 0, 0, 1]]) 113 | # NerF will cycle forward, so lets cycle backward. 114 | shift_coords = np.matrix([ 115 | [0, 0, 1, 0], 116 | [1, 0, 0, 0], 117 | [0, 1, 0, 0], 118 | [0, 0, 0, 1]]) 119 | xf = shift_coords @ extra_xf @ xf_pos 120 | assert np.abs(np.linalg.det(xf) - 1.0) < 1e-4 121 | xf = xf @ xf_rot 122 | return xf 123 | 124 | 125 | average_position_transformed = np.transpose(np.mean([generate_transform_matrix(positions[i], [0,0,0])[:3,3] for i in range(len(names))], axis=0)) 126 | print("Average position transformed: ", average_position_transformed) 127 | 128 | frames = [{ 129 | "file_path": names[i] if args.subdir is None else os.path.join(args.subdir, names[i]), 130 | "transform_matrix": generate_transform_matrix(positions[i], rotations[i]).tolist(), 131 | } for i in range(len(names))] 132 | 133 | transforms_config = { 134 | "camera_angle_x": camera_angle_x, 135 | "scale": 0.2, 136 | "offset": [0.5, 0.5, 0.5], 137 | } 138 | 139 | if args.scene == "barbershop": 140 | transforms_config.update({ 141 | "scale": 0.1, 142 | "offset": [0.5, 0.75, 0.5], 143 | }) 144 | elif args.scene == "garden": 145 | transforms_config.update({ 146 | "scale": 0.1, 147 | "offset": [0.5, 0.5, 0.2], 148 | }) 149 | elif args.scene == "lone_monk": 150 | transforms_config.update({ 151 | "scale": 0.03, 152 | "offset": [0.35, 0.5, 0.2] 153 | }) 154 | elif args.scene == "kitchen": 155 | transforms_config.update({ 156 | "scale": 0.2, 157 | "offset": [0.2, 0.25, 0.5], 158 | }) 159 | 160 | if args.scale is not None: 161 | print("Overriding scale:", args.scale) 162 | transforms_config["scale"] = args.scale 163 | 164 | offset = np.array(transforms_config["offset"]).squeeze() 165 | offset -= transforms_config["scale"] * average_position_transformed.squeeze() 166 | if args.extra_offset is not None: 167 | print("Apply extra offset:", args.extra_offset) 168 | offset += np.array(args.extra_offset) 169 | 170 | transforms_config["offset"] = offset.tolist() 171 | 172 | if args.render_aabb: 173 | transforms_config["render_aabb"] = [args.render_aabb[:3], args.render_aabb[3:]] 174 | 175 | print() 176 | print("Generating config:") 177 | print(transforms_config) 178 | 179 | transforms_config.update({ 180 | "frames": frames, 181 | }) 182 | 183 | 184 | with open(args.output_transforms, "w") as outfile: 185 | json.dump(transforms_config, outfile, indent=4) 186 | -------------------------------------------------------------------------------- /lone_monk_pano.webp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/lone_monk_pano.webp -------------------------------------------------------------------------------- /nerf_barbershop_spherical.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/nerf_barbershop_spherical.gif -------------------------------------------------------------------------------- /nerf_garden.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/nerf_garden.gif -------------------------------------------------------------------------------- /nerf_lone_monk.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/nerf_lone_monk.gif -------------------------------------------------------------------------------- /sha256sums.txt: -------------------------------------------------------------------------------- 1 | d5b3f42debdcf3b5e3e4bb1226b3bcd0e8b85747c27aaad692f8ab029e9593a9 ./lone_monk/lone_monk_LFCuboid_4mx4mx3m.tar 2 | 0868d3c48ed9ddc28b0da91722617668318d483651ce1316933e160c95c364dd ./lone_monk/lone_monk_LFSphere_e220cm_d400cm.tar 3 | 4ee48ef6e28bbac93915800151e76cfdfd14128a05786495e9089f8891178dc0 ./lone_monk/lone_monk_LFCuboid_8panos.tar 4 | 7a64ca400ebe982730013547589a2e2dc6085f08447f631eba27e27ccf2fa616 ./lone_monk/lone_monk_LFSphere_e160cm_d220cm.tar 5 | eb2310d3f59fc9dc728c5b9bfcd8c05787215f9354ac877078701cfab55a454c ./garden/garden_LFCuboid_2x2x1.tar 6 | 09ce4ae63385cfab09508a9201e042089ccb97ea223c32fe94db86145645b7b1 ./garden/garden_LFCuboid_8panos.tar 7 | 4fedb717576d7caa8a3bd92781d423b6511c88c1abbbd9ebfa170cf700e4227c ./garden/garden_LFSphere_e100cm_d50cm.tar 8 | 5bb2cc2085bec651edd44c0739865e78b47a9ab6a2f2609f916d236e3a5dbd08 ./garden/garden_LFSphere_e100cm_d170cm.tar 9 | 4a9714f13b909860fb864d3b6e2f55f790da75d48af24ef6b78c07fc662b371a ./barbershop/barbershop_LFCuboid_8panos.tar 10 | 31ea12f839498f74b396b45600fa2b8b340407a93596dccf095e49ca4c3894fa ./barbershop/barbershop_LFSphere_e105cm_d145cm.tar 11 | b318d5427c4558c7a3e1304215412823a729650732e49535c0e4264e06103687 ./barbershop/barbershop_LFSphere_e110cm_d100cm.tar 12 | 0998a379c1f479618687185e44cb8e94231b8deeca9e7b4198d63a23680bcb3d ./barbershop/barbershop_LFCuboid_1mx3mx1m.tar 13 | -------------------------------------------------------------------------------- /thumbnails/page-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/thumbnails/page-1.png -------------------------------------------------------------------------------- /thumbnails/page-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/thumbnails/page-2.png -------------------------------------------------------------------------------- /thumbnails/page-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/thumbnails/page-3.png -------------------------------------------------------------------------------- /thumbnails/page-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/thumbnails/page-4.png -------------------------------------------------------------------------------- /thumbnails/page-5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/thumbnails/page-5.png -------------------------------------------------------------------------------- /thumbnails/page-6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IDLabMedia/large-lightfields-dataset/cc6daab5f9ec27775d35f83e7c2a811271800cd4/thumbnails/page-6.png --------------------------------------------------------------------------------

{{ page.title | default: site.title | default: site.github.repository_name }}

{{ page.description | default: site.description | default: site.github.project_tagline }}