{"id":13564771,"url":"https://github.com/Lotayou/densebody_pytorch","last_synced_at":"2025-04-03T21:31:37.005Z","repository":{"id":215969948,"uuid":"178356379","full_name":"Lotayou/densebody_pytorch","owner":"Lotayou","description":"PyTorch implementation of CloudWalk's recent work DenseBody","archived":false,"fork":false,"pushed_at":"2019-08-26T03:22:27.000Z","size":4158,"stargazers_count":411,"open_issues_count":13,"forks_count":71,"subscribers_count":21,"default_branch":"master","last_synced_at":"2024-11-04T17:48:07.683Z","etag":null,"topics":["3d-reconstruction","human","pose-estimation","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/pdf/1903.10153.pdf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lotayou.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-03-29T07:38:37.000Z","updated_at":"2024-11-03T03:47:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"171bb40a-40ab-4622-9e62-716b921ad621","html_url":"https://github.com/Lotayou/densebody_pytorch","commit_stats":null,"previous_names":["lotayou/densebody_pytorch"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lotayou%2Fdensebody_pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lotayou%2Fdensebody_pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lotayou%2Fdensebody_pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lotayou%2Fdensebody_pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lotayou","download_url":"https://codeload.github.com/Lotayou/densebody_pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247083522,"owners_count":20880856,"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":["3d-reconstruction","human","pose-estimation","pytorch"],"created_at":"2024-08-01T13:01:35.673Z","updated_at":"2025-04-03T21:31:35.018Z","avatar_url":"https://github.com/Lotayou.png","language":"Python","funding_links":[],"categories":["Python","Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# densebody_pytorch\nPyTorch implementation of CloudWalk's recent paper [DenseBody](https://arxiv.org/abs/1903.10153v3).\n\n**Note**: For most recent updates, please check out the `dev` branch.\n\n**Update on 20190613** A toy dataset has been released to facilitate the reproduction of this project. checkout [`PREPS.md`](PREPS.md) for details.\n\n**Update on 20190826** A pre-trained model ([Encoder](https://yadi.sk/d/isvVFGIU6cHueQ)/[Decoder](https://yadi.sk/d/ck-JBue4XYNpHQ)) has been released to facilitate the reproduction of this project. \n\n![paper teaser](teaser/teaser.jpg)\n\n### Reproduction results\n\nHere is the reproduction result (left: input image; middle: ground truth UV position map; right: estimated UV position map)\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://user-images.githubusercontent.com/33449901/56275710-cce07800-6133-11e9-9507-cfc347a51006.png\" width=\"800px\" /\u003e\n\u003c/div\u003e\n\n### Update Notes\n- SMPL official UV map is now supported! Please checkout [`PREPS.md`](PREPS.md) for details.\n- Code reformating complete! Please refer to `data_utils/UV_map_generator.py` for more details.\n- Thanks [Raj Advani](https://github.com/radvani) for providing new hand crafted UV maps!\n\n### Training Guidelines\nPlease follow the instructions [`PREPS.md`](PREPS.md) to prepare your training dataset and UV maps. Then run `train.sh` or `nohup_train.sh` to begin training. \n\n### Customizations\n\nTo train with your own UV map, checkout [`UV_MAPS.md`](UV_MAPS.md) for detailed instructions.\n\nTo explore different network architectures, checkout [`NETWORKS.md`](NETWORKS.md) for detailed instructions.\n\n### TODO List\n- [x] Creating ground truth UV position maps for Human36m dataset.\n    - [x] [20190329]() Finish UV data processing.\n    - [x] [20190331]() Align SMPL mesh with input image.\n    - [x] [20190404]() Data washing: Image resize to 256*256 and 2D annotation compensation.\n    - [x] [20190411]() Generate and save UV position map.\n        - [x] [radvani](https://github.com/radvani) Hand parsed new 3D UV data\n        - [x] Validity checked with minor artifacts (see results below)\n        - [x] Making UV_map generation module a separate class.\n    - [x] [20190413]() Prepare ground truth UV maps for washed dataset.\n    - [x] [20190417]() SMPL official UV map supported!\n    - [x] [20190613]() A testing toy dataset has been released!\n    \n- [x] Prepare baseline model training\n    - [x] [20190414]() Network design, configs, trainer and dataloader\n    - [x] [20190414]() Baseline complete with first-hand results. Something issue still needs to be addressed.\n    - [x] [20190420]() Testing with different UV maps.\n\n### Authors\n**[Lingbo Yang(Lotayou)](https://github.com/Lotayou)**: The owner and maintainer of this repo.\n\n**[Raj Advani(radvani)](https://github.com/radvani)**: Provide several hand-crafted UV maps and many constructive feedbacks.\n\n### Citation\nPlease consider citing the following paper if you find this project useful.\n\n[DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image](https://arxiv.org/abs/1903.10153v3)\n\n### Acknowledgements\nThe network training part is inspired by [BicycleGAN](https://github.com/junyanz/BicycleGAN)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLotayou%2Fdensebody_pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FLotayou%2Fdensebody_pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLotayou%2Fdensebody_pytorch/lists"}