{"id":18439425,"url":"https://github.com/idiap/gafar","last_synced_at":"2025-04-07T21:32:25.905Z","repository":{"id":208676145,"uuid":"722102749","full_name":"idiap/gafar","owner":"idiap","description":"Geometry-aware Face Reconstruction","archived":false,"fork":false,"pushed_at":"2024-08-24T09:02:25.000Z","size":689,"stargazers_count":11,"open_issues_count":0,"forks_count":2,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-23T01:01:44.960Z","etag":null,"topics":["3d-face","biometrics","face","face-recognition","face-reconstruction","gafar","geometry-aware","nerf","neural-radiance-fields","privacy","security","template-inversion","vulnerability"],"latest_commit_sha":null,"homepage":"https://www.idiap.ch/paper/gafar/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/idiap.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING","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":"2023-11-22T12:48:28.000Z","updated_at":"2024-12-14T13:13:09.000Z","dependencies_parsed_at":null,"dependency_job_id":"3abb52fc-b707-4e9d-8d38-951974da906c","html_url":"https://github.com/idiap/gafar","commit_stats":null,"previous_names":["idiap/gafar"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fgafar","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fgafar/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fgafar/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/idiap%2Fgafar/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/idiap","download_url":"https://codeload.github.com/idiap/gafar/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247732682,"owners_count":20986901,"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":["3d-face","biometrics","face","face-recognition","face-reconstruction","gafar","geometry-aware","nerf","neural-radiance-fields","privacy","security","template-inversion","vulnerability"],"created_at":"2024-11-06T06:24:43.422Z","updated_at":"2025-04-07T21:32:20.889Z","avatar_url":"https://github.com/idiap.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GaFaR: Geometry-aware Face Reconstruction\n\n[Project page](https://www.idiap.ch/paper/gafar/)\n\n![](sample.png)\n\n## Installation\nYou can use the following command to create and activate your Python environment:\n```sh\nconda env create -f environment.yml\nconda activate gafar\n```\n\n## Training face reconstruction model\nWe use [EG3D](https://github.com/NVlabs/eg3d) as a pretrained face generator network based on generative neural radiance fields (GNeRF). Therefore, you need to clone its git repository and download [available pretrained model](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/eg3d):\n```sh\n$ git clone https://github.com/NVlabs/eg3d.git\n```\nWe use `ffhqrebalanced512-128.pkl` [checkpoint](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/eg3d/files) in our experiments.\n\nTo train the face reconstruction model, you can use `train.py`. For example, for blackbox attack against `ElasticFace` using `ArcFace` in loss function, you can use the following commands:\n```sh\npython train.py --path_eg3d_repo \u003cpath_eg3d_repo\u003e  --path_eg3d_checkpoint \u003cpath_eg3d_checkpoint\u003e       \\\n                --FR_system ElasticFace   --FR_loss  ArcFace  --path_ffhq_dataset \u003cpath_ffhq_dataset\u003e  \\\n```\n\n## Pre-trained models (GaFaR Mapping Network)\n[Checkpoints](https://www.idiap.ch/paper/gafar/static/files/checkpoints.zip) of trained models of the mapping network for whitebox and blackbox attacks are available in the [project page](https://www.idiap.ch/paper/gafar/).\n\n\n## Evaluation\nFor evaluation script and also access to the dataset of presentation attack using the reconstructed face images, please check the [project page](https://www.idiap.ch/paper/gafar/).\n\n## Citation\n```bibtex\n  @article{tpami2023ti3d,\n    author    = {Hatef Otroshi Shahreza and S{\\'e}bastien Marcel},\n    title     = {Comprehensive Vulnerability Evaluation of Face Recognition Systems to Template Inversion Attacks Via 3D Face Reconstruction},\n    journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},\n    year      = {2023},\n    volume    = {45},\n    number    = {12},\n    pages     = {14248-14265},\n    doi       = {10.1109/TPAMI.2023.3312123}\n  }\n\n  @inproceedings{iccv2023ti3d,\n    author    = {Hatef Otroshi Shahreza and S{\\'e}bastien Marcel},\n    title     = {Template Inversion Attack against Face Recognition Systems using 3D Face Reconstruction},\n    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},\n    pages     = {19662--19672},\n    month     = {October},\n    year      = {2023}\n  }\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fgafar","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fidiap%2Fgafar","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fidiap%2Fgafar/lists"}