[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72091":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},72091,"sapiens","facebookresearch\u002Fsapiens","facebookresearch","High-resolution models for human tasks.","https:\u002F\u002Fabout.meta.com\u002Frealitylabs\u002Fcodecavatars\u002Fsapiens\u002F",null,"Python",5382,319,43,16,0,1,7,30,3,38.52,"Other",false,"main",[],"2026-06-12 02:02:58","\u003Cp align=\"center\">\n  \u003Cimg src=\".\u002Fassets\u002Fsapiens_animation.gif\" alt=\"Sapiens\" title=\"Sapiens\" width=\"500\"\u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n   \u003Ch2 align=\"center\">Foundation for Human Vision Models\u003C\u002Fh2>\n   \u003Cp align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Frawalkhirodkar.github.io\u002F\">\u003Cstrong>Rawal Khirodkar\u003C\u002Fstrong>\u003C\u002Fa>\n      ·\n      \u003Ca href=\"https:\u002F\u002Fscholar.google.ch\u002Fcitations?user=oLi7xJ0AAAAJ&hl=en\">\u003Cstrong>Timur Bagautdinov\u003C\u002Fstrong>\u003C\u002Fa>\n      ·\n      \u003Ca href=\"https:\u002F\u002Funa-dinosauria.github.io\u002F\">\u003Cstrong>Julieta Martinez\u003C\u002Fstrong>\u003C\u002Fa>\n      ·\n      \u003Ca href=\"https:\u002F\u002Fabout.meta.com\u002Frealitylabs\u002F\">\u003Cstrong>Su Zhaoen\u003C\u002Fstrong>\u003C\u002Fa>\n      ·\n      \u003Ca href=\"https:\u002F\u002Fabout.meta.com\u002Frealitylabs\u002F\">\u003Cstrong>Austin James\u003C\u002Fstrong>\u003C\u002Fa>\n      \u003Cbr>\n      \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fpeter-selednik-05036499\u002F\">\u003Cstrong>Peter Selednik\u003C\u002Fstrong>\u003C\u002Fa>\n      .\n      \u003Ca href=\"https:\u002F\u002Fscholar.google.fr\u002Fcitations?user=8orqBsYAAAAJ&hl=ja\">\u003Cstrong>Stuart Anderson\u003C\u002Fstrong>\u003C\u002Fa>\n      .\n      \u003Ca href=\"https:\u002F\u002Fshunsukesaito.github.io\u002F\">\u003Cstrong>Shunsuke Saito\u003C\u002Fstrong>\u003C\u002Fa>\n   \u003C\u002Fp>\n   \u003Ch3 align=\"center\">ECCV 2024 - Best Paper Candidate\u003C\u002Fh3>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n   \u003Ca href='https:\u002F\u002Fabout.meta.com\u002Frealitylabs\u002Fcodecavatars\u002Fsapiens\u002F'>\n      \u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSapiens-Page-azure?style=for-the-badge&logo=Google%20chrome&logoColor=white&labelColor=000080&color=007FFF' alt='Project Page'>\n   \u003C\u002Fa>\n\n   \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.12569\">\n      \u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPaper-PDF-green?style=for-the-badge&logo=adobeacrobatreader&logoWidth=20&logoColor=white&labelColor=66cc00&color=94DD15' alt='Paper PDF'>\n   \u003C\u002Fa>\n\n   \u003Ca href='https:\u002F\u002Fhuggingface.co\u002Fcollections\u002Ffacebook\u002Fsapiens-66d22047daa6402d565cb2fc'>\n      \u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHuggingFace-Demo-orange?style=for-the-badge&logo=huggingface&logoColor=white&labelColor=FF5500&color=orange' alt='Spaces'>\n   \u003C\u002Fa>\n\n   \u003Ca href='https:\u002F\u002Frawalkhirodkar.github.io\u002Fsapiens\u002F'>\n      \u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMore-Results-ffffff?style=for-the-badge&logo=data:image\u002Fsvg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0id2hpdGUiIHdpZHRoPSIxOCIgaGVpZ2h0PSIxOCI+PHBhdGggZD0iTTAgMGgyNHYyNEgweiIgZmlsbD0ibm9uZSIvPjxwYXRoIGQ9Ik0xOSAzSDVjLTEuMSAwLTIgLjktMiAydjE0YzAgMS4xLjkgMiAyIDJoMTRjMS4xIDAgMi0uOSAyLTJWNWMwLTEuMS0uOS0yLTItMnpNOSAxN0g3di01aDJ2NXptNCAwaC0ydi03aDJ2N3ptNCAwaC0yVjhoMnY5eiIvPjwvc3ZnPg==&logoColor=white&labelColor=8A2BE2&color=9370DB' alt='Results'>\n   \u003C\u002Fa>\n\u003C\u002Fp>\n\nSapiens offers a comprehensive suite for human-centric vision tasks (e.g., 2D pose, part segmentation, depth, normal, etc.). The model family is pretrained on 300 million in-the-wild human images and shows excellent generalization to unconstrained conditions. These models are also designed for extracting high-resolution features, having been natively trained at a 1024 x 1024 image resolution with a 16-pixel patch size.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\".\u002Fassets\u002F01.gif\" alt=\"01\" title=\"01\" width=\"400\"\u002F>\n  \u003Cimg src=\".\u002Fassets\u002F03.gif\" alt=\"03\" title=\"03\" width=\"400\"\u002F>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Cimg src=\".\u002Fassets\u002F02.gif\" alt=\"02\" title=\"02\" width=\"400\"\u002F>\n  \u003Cimg src=\".\u002Fassets\u002F04.gif\" alt=\"04\" title=\"04\" width=\"400\"\u002F>\n\u003C\u002Fp>\n\n\n## 🚀 Getting Started\n\n### Clone the Repository\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fsapiens.git\n   export SAPIENS_ROOT=\u002Fpath\u002Fto\u002Fsapiens\n   ```\n\n### Recommended: Lite Installation (Inference-only)\n   For users setting up their own environment primarily for running existing models in inference mode, we recommend the [Sapiens-Lite installation](lite\u002FREADME.md).\\\n   This setup offers optimized inference (4x faster) with minimal dependencies (only PyTorch + numpy + cv2).\n\n### Full Installation\n   To replicate our complete training setup, run the provided installation script. \\\n   This will create a new conda environment named `sapiens` and install all necessary dependencies.\n\n   ```bash\n   cd $SAPIENS_ROOT\u002F_install\n   .\u002Fconda.sh\n   ```\n\n   Please download the **original** checkpoints from [hugging-face](https:\u002F\u002Fhuggingface.co\u002Ffacebook\u002Fsapiens). \\\n   You can be selective about only downloading the checkpoints of interest.\\\n   Set `$SAPIENS_CHECKPOINT_ROOT` to be the path to the `sapiens_host` folder. Place the checkpoints following this directory structure:\n   ```plaintext\n   sapiens_host\u002F\n   ├── detector\u002F\n   │   └── checkpoints\u002F\n   │       └── rtmpose\u002F\n   ├── pretrain\u002F\n   │   └── checkpoints\u002F\n   │       ├── sapiens_0.3b\u002F\n               ├── sapiens_0.3b_epoch_1600_clean.pth\n   │       ├── sapiens_0.6b\u002F\n               ├── sapiens_0.6b_epoch_1600_clean.pth\n   │       ├── sapiens_1b\u002F\n   │       └── sapiens_2b\u002F\n   ├── pose\u002F\n      └── checkpoints\u002F\n         ├── sapiens_0.3b\u002F\n   └── seg\u002F\n   └── depth\u002F\n   └── normal\u002F\n   ```\n\n## 🌟 Human-Centric Vision Tasks\nWe finetune sapiens for multiple human-centric vision tasks. Please checkout the list below.\n\n- ###  [Image Encoder](docs\u002FPRETRAIN_README.md) \u003Csup>\u003Csmall>\u003Ca href=\"lite\u002Fdocs\u002FPRETRAIN_README.md\" style=\"color: #FFA500;\">[lite]\u003C\u002Fa>\u003C\u002Fsmall>\u003C\u002Fsup>\n- ### [Pose Estimation](docs\u002FPOSE_README.md) \u003Csup>\u003Csmall>\u003Ca href=\"lite\u002Fdocs\u002FPOSE_README.md\" style=\"color: #FFA500;\">[lite]\u003C\u002Fa>\u003C\u002Fsmall>\u003C\u002Fsup>\n- ### [Body Part Segmentation](docs\u002FSEG_README.md) \u003Csup>\u003Csmall>\u003Ca href=\"lite\u002Fdocs\u002FSEG_README.md\" style=\"color: #FFA500;\">[lite]\u003C\u002Fa>\u003C\u002Fsmall>\u003C\u002Fsup>\n- ### [Depth Estimation](docs\u002FDEPTH_README.md) \u003Csup>\u003Csmall>\u003Ca href=\"lite\u002Fdocs\u002FDEPTH_README.md\" style=\"color: #FFA500;\">[lite]\u003C\u002Fa>\u003C\u002Fsmall>\u003C\u002Fsup>\n- ### [Surface Normal Estimation](docs\u002FNORMAL_README.md) \u003Csup>\u003Csmall>\u003Ca href=\"lite\u002Fdocs\u002FNORMAL_README.md\" style=\"color: #FFA500;\">[lite]\u003C\u002Fa>\u003C\u002Fsmall>\u003C\u002Fsup>\n\n## 🎯 Easy Steps to Finetuning Sapiens\nFinetuning our models is super-easy! Here is a detailed training guide for the following tasks.\n- ### [Pose Estimation](docs\u002Ffinetune\u002FPOSE_README.md)\n- ### [Body-Part Segmentation](docs\u002Ffinetune\u002FSEG_README.md)\n- ### [Depth Estimation](docs\u002Ffinetune\u002FDEPTH_README.md)\n- ### [Surface Normal Estimation](docs\u002Ffinetune\u002FNORMAL_README.md)\n\n## 📈 Quantitative Evaluations\n- ### [Pose Estimation](docs\u002Fevaluate\u002FPOSE_README.md)\n\n## 🤝 Acknowledgements & Support & Contributing\nWe would like to acknowledge the work by [OpenMMLab](https:\u002F\u002Fgithub.com\u002Fopen-mmlab) which this project benefits from.\\\nFor any questions or issues, please open an issue in the repository.\\\nSee [contributing](CONTRIBUTING.md) and the [code of conduct](CODE_OF_CONDUCT.md).\n\n## License\nThis project is licensed under [LICENSE](LICENSE).\\\nPortions derived from open-source projects are licensed under [Apache 2.0](https:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0).\n\n## 📚 Citation\nIf you use Sapiens in your research, please consider citing us.\n```bibtex\n@article{khirodkar2024sapiens,\n  title={Sapiens: Foundation for Human Vision Models},\n  author={Khirodkar, Rawal and Bagautdinov, Timur and Martinez, Julieta and Zhaoen, Su and James, Austin and Selednik, Peter and Anderson, Stuart and Saito, Shunsuke},\n  journal={arXiv preprint arXiv:2408.12569},\n  year={2024}\n}\n```\n","Sapiens 是一个专注于人类视觉任务的高分辨率模型库，能够处理如2D姿态估计、部位分割、深度和法线等任务。该项目基于3亿张真实世界的人类图片进行预训练，展现出在无约束条件下的出色泛化能力。其核心功能包括从1024x1024分辨率图像中提取高精度特征，使用16像素大小的patch进行原生训练，确保了对细节的精准捕捉。Sapiens适用于需要高质量人体分析的各种场景，比如虚拟现实、增强现实应用开发以及高级人机交互系统的设计。",2,"2026-06-11 03:40:18","high_star"]