{"id":19529277,"url":"https://github.com/isl-org/redwood-3dscan","last_synced_at":"2025-04-26T11:34:34.949Z","repository":{"id":40647881,"uuid":"303372838","full_name":"isl-org/redwood-3dscan","owner":"isl-org","description":null,"archived":false,"fork":false,"pushed_at":"2022-04-08T05:54:35.000Z","size":176,"stargazers_count":106,"open_issues_count":0,"forks_count":16,"subscribers_count":7,"default_branch":"master","last_synced_at":"2023-10-20T20:27:24.169Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/isl-org.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-10-12T11:39:47.000Z","updated_at":"2023-09-26T09:11:30.000Z","dependencies_parsed_at":"2022-08-27T01:50:17.253Z","dependency_job_id":null,"html_url":"https://github.com/isl-org/redwood-3dscan","commit_stats":null,"previous_names":[],"tags_count":1,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fredwood-3dscan","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fredwood-3dscan/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fredwood-3dscan/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2Fredwood-3dscan/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/isl-org","download_url":"https://codeload.github.com/isl-org/redwood-3dscan/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224033568,"owners_count":17244618,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-11T01:23:19.383Z","updated_at":"2024-11-11T01:23:21.026Z","avatar_url":"https://github.com/isl-org.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DISCONTINUATION OF PROJECT #  \nThis project will no longer be maintained by Intel.  \nIntel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.  \nIntel no longer accepts patches to this project.  \n If you have an ongoing need to use this project, are interested in independently developing it, or would like to maintain patches for the open source software community, please create your own fork of this project.  \n  \n# A Large Dataset of Object Scans (redwood-3dscan)\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"http://redwood-data.org/3dscan/img/teaser.jpg\" width=\"640\" /\u003e\n\u003c/p\u003e\n\n## Abstract\n\nWe have created a dataset of more than ten thousand 3D scans of real objects.\nTo create the dataset, we recruited 70 operators, equipped them with\nconsumer-grade mobile 3D scanning setups, and paid them to scan objects in\ntheir environments. The operators scanned objects of their choosing, outside the\nlaboratory and without direct supervision by computer vision professionals. The\nresult is a large and diverse collection of object scans: from shoes, mugs, and\ntoys to grand pianos, construction vehicles, and large outdoor sculptures. We\nworked with an attorney to ensure that data acquisition did not violate privacy\nconstraints. The acquired data was irrevocably placed in the public domain and\nis available freely.\n\nYou can preview and explore the dataset at\n[http://redwood-data.org/3dscan/](http://redwood-data.org/3dscan/).\n\n## Dataset organization\n\nIf you use our download scripts, the downloaded dataset will be stored in `data/`.\n\n```txt\ndata\n├── rgbd (10,933 RGBD scans, each contains multiple RGB and depth images)\n│   ├── 00001.zip\n│   ├── 00002.zip\n│   ├── ...\n│   ├── 11097.zip\n│   └── 11098.zip\n├── mesh (441 reconstructed models)\n│   ├── 00004.ply\n│   ├── 00033.ply\n│   ├── ...\n│   ├── 10548.ply\n│   └── 10664.ply\n└── video (10,933 videos created from images)\n    ├── 00001.mp4\n    ├── 00002.mp4\n    ├── ...\n    ├── 11097.mp4\n    └── 11098.mp4\n```\n\n- Dataset size: The entire dataset is ~4TB in size.\n- RGBD scans: There are 10,933 RGBD scans. Each scan contains multiple RGBD images.\n- Meshes: There are 441 reconstructed mesh models.\n- Videos: There are 10,933 videos, created from RGBD images.\n- Categories: 9,131 RGBD scans are categorized into 320 categories. Each scan has at most one category.\n\n## Example usage\n\n```python\nimport redwood_3dscan as rws\n\n# Print RGBD scans (list)\nprint(rws.rgbds)\n\n# Print meshes (list)\nprint(rws.meshes)\n\n# Print categories (dict: string-\u003elist)\nprint(rws.categories)\n\n# Print all scan_id of the \"sofa\" category\nprint(rws.categories[\"sofa\"])\n\n# Download by scan_id \"00033\"\n# Download will be skipped if the resource is unavailable\n# e.g. some RGBD images may not come with mesh.\nrws.download_rgbd(\"00033\")  # Save to data/rgbd/00033.zip, if available\nrws.download_mesh(\"00033\")  # Save to data/mesh/00033.ply, if available\nrws.download_video(\"00033\") # Save to data/video/00033.mp4, if available\nrws.download_all(\"00033\")   # Downloads rgbd, mesh, and video together\n\n# Download by category \"sofa\"\nrws.download_category(\"sofa\")\n```\n\nYou can use\n[Open3D](https://github.com/intel-isl/Open3D) to load and visualize the models.\n\n```shell\n# For installation guides, see:\n# http://www.open3d.org/docs/release/getting_started.html\npip install open3d\n```\n\n```python\nimport redwood_3dscan as rws\nimport open3d as o3d\n\nrws.download_mesh(\"00033\")\nmesh = o3d.io.read_triangle_mesh(\"data/mesh/00033.ply\")\nmesh.compute_vertex_normals()\no3d.visualization.draw_geometries([mesh])\n```\n\n![Open3D Visualizer](assets/open3d_vis.png)\n\n## License\n\nThe entire dataset, including both RGB-D scans and reconstructed models, is in\nthe [public domain](https://wiki.creativecommons.org/wiki/Public_domain). Any\npart of the dataset can be used for any purpose with proper attribution. If\nyou use any of the data, please cite\n[our technical report](http://arxiv.org/abs/1602.02481).\n\n```bibtex\n@article{Choi2016,\n          author    = {Sungjoon Choi and Qian-Yi Zhou and Stephen Miller and Vladlen Koltun},\n          title     = {A Large Dataset of Object Scans},\n          journal   = {arXiv:1602.02481},\n          year      = {2016},\n        }\n```\n\n## File Format\n\nThe RGB-D sequences were acquired with PrimeSense Carmine cameras. The\nresolution is 640×480, the frame rate is 30Hz. Each scan is packaged in a zip\narchive that contains consecutive color images stored as JPG and depth images\nstored as 16-bit PNG, where pixel values represent depth in millimeters. The\nfirst part of a file name indicates the frame number and the second part\nprovides a time stamp in microseconds.\n\nThe focal length is 525 for both axes and the principal point is (319.5, 239.5).\nThe depth images are registered to the color images.\n\nThe reconstructed models are all in\n[PLY file format](https://en.wikipedia.org/wiki/PLY_(file_format)).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fredwood-3dscan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fisl-org%2Fredwood-3dscan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fredwood-3dscan/lists"}