{"id":31580424,"url":"https://github.com/ollieboyne/found","last_synced_at":"2025-10-05T21:12:22.203Z","repository":{"id":204120477,"uuid":"709275550","full_name":"OllieBoyne/FOUND","owner":"OllieBoyne","description":"Official code for FOUND: Foot Optimisation with Uncertain Normals for Surface Deformation using Synthetic Data","archived":false,"fork":false,"pushed_at":"2025-02-12T18:07:07.000Z","size":28734,"stargazers_count":51,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-02-12T19:24:39.097Z","etag":null,"topics":["3d-reconstruction","computer-vision","surface-normals","surface-normals-estimation","surface-reconstruction"],"latest_commit_sha":null,"homepage":"http://www.ollieboyne.com/FOUND/","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/OllieBoyne.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":"2023-10-24T11:46:42.000Z","updated_at":"2025-02-12T18:07:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"4ba88dbb-71f6-437d-aee5-6c6465519c98","html_url":"https://github.com/OllieBoyne/FOUND","commit_stats":null,"previous_names":["ollieboyne/found"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/OllieBoyne/FOUND","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OllieBoyne%2FFOUND","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OllieBoyne%2FFOUND/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OllieBoyne%2FFOUND/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OllieBoyne%2FFOUND/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OllieBoyne","download_url":"https://codeload.github.com/OllieBoyne/FOUND/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OllieBoyne%2FFOUND/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278520015,"owners_count":26000401,"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","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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","computer-vision","surface-normals","surface-normals-estimation","surface-reconstruction"],"created_at":"2025-10-05T21:12:21.096Z","updated_at":"2025-10-05T21:12:22.196Z","avatar_url":"https://github.com/OllieBoyne.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"http://ollieboyne.github.io/FOUND\"\u003e\n        \u003cimg width=70% src=\"https://ollieboyne.github.io/FOUND/images/logos/found_v1.png\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\nThis repository contains the code for 3D shape fitting to predicted surface normals, as shown in our paper:\n\n\u003e **FOUND: \u003cins\u003eF\u003c/ins\u003eoot \u003cins\u003eO\u003c/ins\u003eptimisation with \u003cins\u003eU\u003c/ins\u003encertain \u003cins\u003eN\u003c/ins\u003eormals for Surface \u003cins\u003eD\u003c/ins\u003eeformation using Synthetic Data**  \\\n\u003e Winter Conference on Applications of Computer Vision 2024 \\\n\u003e [Oliver Boyne](https://ollieboyne.github.io), [Gwangbin Bae](https://www.baegwangbin.com/), [James Charles](http://www.jjcvision.com), and [Roberto Cipolla](https://mi.eng.cam.ac.uk/~cipolla/) \\\n\u003e [[arXiv]](https://arxiv.org/abs/2310.18279) [[project page]](https://ollieboyne.github.io/FOUND/)\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"http://ollieboyne.github.io/FOUND\"\u003e\n        \u003cimg width=90% src=\"https://ollieboyne.github.io/FOUND/images/itw/sliders.gif\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n**[Feb 2025]** Check out our new work on recovering the FIND model from images using dense correspondences! [[FOCUS]](https://www.ollieboyne.com/FOCUS)\n\n## Quickstart\n\n1) `git clone --recurse-submodules http://github.com/OllieBoyne/FOUND`\n2) Install dependencies: `pip install -r requirements.txt`\n3) Download the [pretrained FIND model](https://drive.google.com/drive/folders/1XWmEVo3AdnhJU2fs6igls-emp93beQpm?usp=share_link) to `data/find_nfap`\n4) Download our [benchmark foot dataset](https://github.com/OllieBoyne/Foot3D) to `data/scans`\n5) Fit a single scan:\n\n```\npython FOUND/fit.py --exp_name \u003cexp_name\u003e --data_folder \u003cdata_folder\u003e\n```\n\nYou can use `--cfg \u003cfile\u003e.yaml` to use a config file to set parameters. See [`args.py`](utils/args.py) for all arguments, and [`example-cfg.yaml`](example-cfg.yaml) for an example config file.\n\n6) Evaluate all of our reconstruction dataset:\n\n```\npython FOUND/eval.py --data_folder \u003cdata_folder\u003e --gpus \u003cgpu_indices\u003e\n```\n\ngpu_indices is a space separated list, e.g. `--gpus 0 1 2 3`\n\n\n## Data\n\nWe provide our synthetic foot dataset, [SynFoot](https://github.com/OllieBoyne/SynFoot), which contains 50K synthetic foot scans, with RGB, normals, and masks.\n\nWe also provide a benchmark multiview evaluative dataset, [Foot3D](https://github.com/OllieBoyne/Foot3D).\n\n\n### Related work\n\nPlease check out all of our projects that built into this work!\n\n- [FIND - Generative foot model](https://ollieboyne.github.io/FIND)\n- [Surface Normal Estimation w/ Uncertainty](https://github.com/baegwangbin/surface_normal_uncertainty)\n- [BlenderSynth - Synthetic data generation](https://ollieboyne.github.io/BlenderSynth)\n\n\n### Citation\n\nIf you use our work, please cite:\n\n```\n@inproceedings{boyne2024found,\n            title={FOUND: {F}oot {O}ptimisation with {U}ncertain {N}ormals for Surface {D}eformation using Synthetic Data},\n            author={Boyne, Oliver and Bae, Gwangbin and Charles, James and Cipolla, Roberto},\n            booktitle={Winter Conference on Applications of Computer Vision (WACV)},\n            year={2024}\n}\n```\n\n\n### Troubleshooting\n\nIf you have any issues with `trimesh` and `shapely`, see [misc/shapely.md](misc/shapely.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Follieboyne%2Ffound","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Follieboyne%2Ffound","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Follieboyne%2Ffound/lists"}