{"id":13441504,"url":"https://github.com/gaomingqi/Track-Anything","last_synced_at":"2025-03-20T12:31:13.807Z","repository":{"id":153234152,"uuid":"626676185","full_name":"gaomingqi/Track-Anything","owner":"gaomingqi","description":"Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.","archived":false,"fork":false,"pushed_at":"2024-05-31T01:13:00.000Z","size":352438,"stargazers_count":6440,"open_issues_count":105,"forks_count":480,"subscribers_count":62,"default_branch":"master","last_synced_at":"2024-10-15T09:41:08.920Z","etag":null,"topics":["inpaint-anything","interactive-tracking","segment-anything","track-anything","video-object-segmentation","video-object-tracking"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gaomingqi.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":"2023-04-12T00:19:57.000Z","updated_at":"2024-10-15T05:16:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"424ddbfd-f39a-4a23-831b-0ad90c91c738","html_url":"https://github.com/gaomingqi/Track-Anything","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/gaomingqi%2FTrack-Anything","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaomingqi%2FTrack-Anything/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaomingqi%2FTrack-Anything/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gaomingqi%2FTrack-Anything/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gaomingqi","download_url":"https://codeload.github.com/gaomingqi/Track-Anything/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221760017,"owners_count":16876337,"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":["inpaint-anything","interactive-tracking","segment-anything","track-anything","video-object-segmentation","video-object-tracking"],"created_at":"2024-07-31T03:01:34.819Z","updated_at":"2025-03-20T12:31:13.801Z","avatar_url":"https://github.com/gaomingqi.png","language":"Python","funding_links":[],"categories":["Python","Recent Works","\u003cspan id=\"video\"\u003eVideo\u003c/span\u003e","Summary","Repos","Paper List","Uncategorized","AI \u0026 Machine Learning for CG"],"sub_categories":["\u003cspan id=\"tool\"\u003eLLM (LLM \u0026 Tool)\u003c/span\u003e","Follow-up Papers","Uncategorized","AI-Assisted CG Tools"],"readme":"\u003c!-- ![](./assets/track-anything-logo.jpg) --\u003e\n\n\u003cdiv align=center\u003e\n\u003cimg src=\"./assets/track-anything-logo.jpg\"/\u003e\n\u003c/div\u003e\n\u003cbr/\u003e\n\u003cdiv align=center\u003e\n\u003ca src=\"https://img.shields.io/badge/%F0%9F%93%96-Arxiv_2304.11968-red.svg?style=flat-square\" href=\"https://arxiv.org/abs/2304.11968\"\u003e\n\u003cimg src=\"https://img.shields.io/badge/%F0%9F%93%96-Arxiv_2304.11968-red.svg?style=flat-square\"\u003e\n\u003c/a\u003e\n\u003ca src=\"https://img.shields.io/badge/%F0%9F%A4%97-Open_in_Spaces-informational.svg?style=flat-square\" href=\"https://huggingface.co/spaces/VIPLab/Track-Anything?duplicate=true\"\u003e\n\u003cimg src=\"https://img.shields.io/badge/%F0%9F%A4%97-Hugging_Face_Space-informational.svg?style=flat-square\"\u003e\n\u003c/a\u003e\n\u003ca src=\"https://img.shields.io/badge/%F0%9F%97%BA-Tutorials in Steps-2bb7b3.svg?style=flat-square\" href=\"./doc/tutorials.md\"\u003e\n\u003cimg src=\"https://img.shields.io/badge/%F0%9F%97%BA-Tutorials in Steps-2bb7b3.svg?style=flat-square\"\u003e\n\n\u003c/a\u003e\n\u003ca src=\"https://img.shields.io/badge/%F0%9F%9A%80-SUSTech_VIP_Lab-ed6c00.svg?style=flat-square\" href=\"https://zhengfenglab.com/\"\u003e\n\u003cimg src=\"https://img.shields.io/badge/%F0%9F%9A%80-SUSTech_VIP_Lab-ed6c00.svg?style=flat-square\"\u003e\n\u003c/a\u003e\n\u003c/div\u003e\n\n***Track-Anything*** is a flexible and interactive tool for video object tracking and segmentation. It is developed upon [Segment Anything](https://github.com/facebookresearch/segment-anything), can specify anything to track and segment via user clicks only. During tracking, users can flexibly change the objects they wanna track or correct the region of interest if there are any ambiguities. These characteristics enable ***Track-Anything*** to be suitable for: \n- Video object tracking and segmentation with shot changes. \n- Visualized development and data annotation for video object tracking and segmentation.\n- Object-centric downstream video tasks, such as video inpainting and editing. \n\n\u003cdiv align=center\u003e\n\u003cimg src=\"./assets/avengers.gif\" width=\"81%\"/\u003e\n\u003c/div\u003e\n\n\u003c!-- ![avengers]() --\u003e\n\n## :rocket: Updates\n\n- 2023/05/02: We uploaded tutorials in steps :world_map:. Check [HERE](./doc/tutorials.md) for more details.\n\n- 2023/04/29: We improved inpainting by decoupling GPU memory usage and video length. Now Track-Anything can inpaint videos with any length! :smiley_cat: Check [HERE](https://github.com/gaomingqi/Track-Anything/issues/4#issuecomment-1528198165) for our GPU memory requirements. \n\n- 2023/04/25: We are delighted to introduce [Caption-Anything](https://github.com/ttengwang/Caption-Anything) :writing_hand:, an inventive project from our lab that combines the capabilities of Segment Anything, Visual Captioning, and ChatGPT. \n\n- 2023/04/20: We deployed [DEMO](https://huggingface.co/spaces/VIPLab/Track-Anything?duplicate=true) on Hugging Face :hugs:!\n\n- 2023/04/14: We made Track-Anything public!\n\n## :world_map: Video Tutorials ([Track-Anything Tutorials in Steps](./doc/tutorials.md))\n\nhttps://user-images.githubusercontent.com/30309970/234902447-a4c59718-fcfe-443a-bd18-2f3f775cfc13.mp4\n\n---\n\n### :joystick: Example - Multiple Object Tracking and Segmentation (with [XMem](https://github.com/hkchengrex/XMem))\n\nhttps://user-images.githubusercontent.com/39208339/233035206-0a151004-6461-4deb-b782-d1dbfe691493.mp4\n\n---\n\n### :joystick: Example - Video Object Tracking and Segmentation with Shot Changes (with [XMem](https://github.com/hkchengrex/XMem))\n\nhttps://user-images.githubusercontent.com/30309970/232848349-f5e29e71-2ea4-4529-ac9a-94b9ca1e7055.mp4\n\n---\n\n### :joystick: Example - Video Inpainting (with [E2FGVI](https://github.com/MCG-NKU/E2FGVI))\n\nhttps://user-images.githubusercontent.com/28050374/232959816-07f2826f-d267-4dda-8ae5-a5132173b8f4.mp4\n\n## :computer: Get Started\n#### Linux \u0026 Windows\n```shell\n# Clone the repository:\ngit clone https://github.com/gaomingqi/Track-Anything.git\ncd Track-Anything\n\n# Install dependencies: \npip install -r requirements.txt\n\n# Run the Track-Anything gradio demo.\npython app.py --device cuda:0\n# python app.py --device cuda:0 --sam_model_type vit_b # for lower memory usage\n```\n\n\n## :book: Citation\nIf you find this work useful for your research or applications, please cite using this BibTeX:\n```bibtex\n@misc{yang2023track,\n      title={Track Anything: Segment Anything Meets Videos}, \n      author={Jinyu Yang and Mingqi Gao and Zhe Li and Shang Gao and Fangjing Wang and Feng Zheng},\n      year={2023},\n      eprint={2304.11968},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n## :clap: Acknowledgements\n\nThe project is based on [Segment Anything](https://github.com/facebookresearch/segment-anything), [XMem](https://github.com/hkchengrex/XMem), and [E2FGVI](https://github.com/MCG-NKU/E2FGVI). Thanks for the authors for their efforts.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaomingqi%2FTrack-Anything","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgaomingqi%2FTrack-Anything","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaomingqi%2FTrack-Anything/lists"}