{"data":{"slug":"zc-alexfan-hold","name":"hold","tagline":"[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D","github_url":"https://github.com/zc-alexfan/hold","owner":"zc-alexfan","repo":"hold","owner_avatar_url":"https://avatars.githubusercontent.com/u/38775813?v=4","primary_language":"Python","stars":486,"forks":15,"topics":["3d-reconstruction","ai","artificial-intelligence","augmented-reality","computer-vision","hand-object-interaction","hand-object-reconstruction","hand-tracking","mano","mixed-reality","neural-networks","pose-estimation","pytorch","virtual-reality"],"archived":false,"github_pushed_at":"2026-03-10T17:45:07+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/zc-alexfan-hold","markdown_url":"https://www.graphcanon.com/tools/zc-alexfan-hold.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zc-alexfan-hold","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zc-alexfan-hold","description":"[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.","homepage_url":"https://zc-alexfan.github.io/hold","license":"MIT","open_issues":9,"watchers":11,"ai_summary":null,"readme_excerpt":"### Getting started\n\nGet a copy of the code:\n\n```bash\ngit clone https://github.com/zc-alexfan/hold.git\ncd hold; git submodule update --init --recursive\n```\n\n1. **Setup environments**\n    - Follow the instructions here: [`docs/setup.md`](docs/setup.md).\n    - You may skip external dependencies for now.\n\n1. **Train on a preprocessed sequence**\n   - Start with one of our preprocessed in-the-wild sequences, such as `hold_bottle1_itw`.\n   - Familiarize yourself with the usage guidelines in [`docs/usage.md`](docs/usage.md) for this preprocessed sequence.\n   - This will enable you to train, render HOLD, and experiment with our interactive viewer.\n   - At this stage, you can also explore the HOLD code in the `./code` directory.\n\n1. **Set up external dependencies and process custom videos**\n   - After understanding the initial tools, set up the \"external dependencies\" as outlined in [`docs/setup.md`](docs/setup.md).\n   - Preprocess the images from the `hold_bottle1_itw` sequence by following the instructions in [`docs/custom.md`](docs/custom.md).\n   - Train on this sequence to learn how to build a custom dataset.\n   - You can capture your own custom video and reconstruct it in 3D at this point.\n   - Most preprocessing artifact files are documented in [`docs/data_doc.md`](docs/data_doc.md), which you can use as a reference.\n\n1. **Two-hand setting**: Bimanual category-agnostic reconstruction\n    - At this point, you can preprocess and train on a custom single-hand sequence. \n    - Now you can take on the bimanual category-agnostic reconstruction challenge!\n    - Following the instruction in [`docs/arctic.md`](docs/arctic.md) to reconstruct two-hand manipulation of ARCTIC sequences.","github_created_at":"2023-11-30T10:53:07+00:00","created_at":"2026-07-11T12:29:23.359787+00:00","updated_at":"2026-07-11T12:29:30.602214+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"}],"tags":[{"slug":"3d-reconstruction","name":"3d-reconstruction"},{"slug":"hand-object-reconstruction","name":"hand-object-reconstruction"},{"slug":"ai","name":"ai"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"hand-object-interaction","name":"hand-object-interaction"},{"slug":"hand-tracking","name":"hand-tracking"},{"slug":"augmented-reality","name":"augmented-reality"},{"slug":"computer-vision","name":"computer-vision"}],"trust":{"provenance":{"is_fork":false,"github_id":725535660,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:29:24.617Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":122,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":9,"high_count":0,"last_scan_at":"2026-07-11T12:29:27.585Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:29:27.246Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T12:29:27.246Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T12:29:27.246Z"}}}}