{"id":13427014,"url":"https://github.com/facebookresearch/DensePose","last_synced_at":"2025-03-15T22:31:42.599Z","repository":{"id":39311284,"uuid":"136069311","full_name":"facebookresearch/DensePose","owner":"facebookresearch","description":"A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body","archived":true,"fork":false,"pushed_at":"2023-01-18T17:26:59.000Z","size":12288,"stargazers_count":7017,"open_issues_count":151,"forks_count":1299,"subscribers_count":250,"default_branch":"main","last_synced_at":"2025-02-23T00:14:08.970Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://densepose.org","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/facebookresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-06-04T18:52:54.000Z","updated_at":"2025-02-19T09:16:35.000Z","dependencies_parsed_at":"2023-02-10T16:30:30.861Z","dependency_job_id":null,"html_url":"https://github.com/facebookresearch/DensePose","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FDensePose","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FDensePose/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FDensePose/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FDensePose/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/facebookresearch","download_url":"https://codeload.github.com/facebookresearch/DensePose/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243801601,"owners_count":20350105,"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":"2024-07-31T00:01:50.927Z","updated_at":"2025-03-15T22:31:37.567Z","avatar_url":"https://github.com/facebookresearch.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","Popular implementations","Computer Vision","Deep Learning","Datasets","📦 Legacy \u0026 Inactive Projects","Pose Estimation"],"sub_categories":["Others","Notable Projects","🔍 **Quick Access**","Physics-Based Controller","Implementations"],"readme":"# DensePose: \n**Dense Human Pose Estimation In The Wild**\n\n_Rıza Alp Güler, Natalia Neverova, Iasonas Kokkinos_\n\n[[`densepose.org`](https://densepose.org)] [[`arXiv`](https://arxiv.org/abs/1802.00434)] [[`BibTeX`](#CitingDensePose)]\n\nDense human pose estimation aims at mapping all human pixels of an RGB image to the 3D surface of the human body. \nDensePose-RCNN is implemented in the [Detectron](https://github.com/facebookresearch/Detectron) framework and is powered by [Caffe2](https://github.com/caffe2/caffe2).\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://drive.google.com/uc?export=view\u0026id=1qfSOkpueo1kVZbXOuQJJhyagKjMgepsz\" width=\"700px\" /\u003e\n\u003c/div\u003e\n\n\nIn this repository, we provide the code to train and evaluate DensePose-RCNN. We also provide notebooks to visualize the collected DensePose-COCO dataset and show the correspondences to the SMPL model.\n\n## Important Note\n\n**!!! This project is no longer supported !!!**\n\nDensePose is now part of Detectron2 (https://github.com/facebookresearch/detectron2/tree/master/projects/DensePose). There you can find the most up to date architectures / models. If you think some feature is missing from there, please post an issue in [Detectron2 DensePose](https://github.com/facebookresearch/detectron2/tree/master/projects/DensePose).\n\n## Installation\n\nPlease find installation instructions for Caffe2 and DensePose in [`INSTALL.md`](INSTALL.md), a document based on the [Detectron](https://github.com/facebookresearch/Detectron) installation instructions.\n\n## Inference-Training-Testing\n\nAfter installation, please see [`GETTING_STARTED.md`](GETTING_STARTED.md)  for examples of inference and training and testing.\n\n## Notebooks\n\n### Visualization of DensePose-COCO annotations:\n\nSee [`notebooks/DensePose-COCO-Visualize.ipynb`](notebooks/DensePose-COCO-Visualize.ipynb) to visualize the DensePose-COCO annotations on the images:\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://drive.google.com/uc?export=view\u0026id=1uYRJkIA24KkJU2i4sMwrKa61P0xtZzHk\" width=\"800px\" /\u003e\n\u003c/div\u003e\n\n---\n\n### DensePose-COCO in 3D:\n\nSee [`notebooks/DensePose-COCO-on-SMPL.ipynb`](notebooks/DensePose-COCO-on-SMPL.ipynb) to localize the DensePose-COCO annotations on the 3D template ([`SMPL`](http://smpl.is.tue.mpg.de)) model:\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://drive.google.com/uc?export=view\u0026id=1m32oyMuE7AZd3EOf9k8zHpr75C8bHlYj\" width=\"500px\" /\u003e\n\u003c/div\u003e\n\n---\n### Visualize DensePose-RCNN Results:\n\nSee [`notebooks/DensePose-RCNN-Visualize-Results.ipynb`](notebooks/DensePose-RCNN-Visualize-Results.ipynb) to visualize the inferred DensePose-RCNN Results.\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://drive.google.com/uc?export=view\u0026id=1k4HtoXpbDV9MhuyhaVcxDrXnyP_NX896\" width=\"900px\" /\u003e\n\u003c/div\u003e\n\n---\n### DensePose-RCNN Texture Transfer:\n\nSee [`notebooks/DensePose-RCNN-Texture-Transfer.ipynb`](notebooks/DensePose-RCNN-Texture-Transfer.ipynb) to localize the DensePose-COCO annotations on the 3D template ([`SMPL`](http://smpl.is.tue.mpg.de)) model:\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://drive.google.com/uc?export=view\u0026id=1r-w1oDkDHYnc1vYMbpXcYBVD1-V3B4Le\" width=\"900px\" /\u003e\n\u003c/div\u003e\n\n## License\n\nThis source code is licensed under the license found in the [`LICENSE`](LICENSE) file in the root directory of this source tree.\n\n## \u003ca name=\"CitingDensePose\"\u003e\u003c/a\u003eCiting DensePose\n\nIf you use Densepose, please use the following BibTeX entry.\n\n```\n  @InProceedings{Guler2018DensePose,\n  title={DensePose: Dense Human Pose Estimation In The Wild},\n  author={R\\{i}za Alp G\\\"uler, Natalia Neverova, Iasonas Kokkinos},\n  journal={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year={2018}\n  }\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2FDensePose","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffacebookresearch%2FDensePose","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2FDensePose/lists"}