{"id":21340984,"url":"https://github.com/aashishrai3799/3dfacecam","last_synced_at":"2025-07-12T14:33:41.046Z","repository":{"id":58942996,"uuid":"506003233","full_name":"aashishrai3799/3DFaceCAM","owner":"aashishrai3799","description":"Implementation of a 3D Face Generative Model","archived":false,"fork":false,"pushed_at":"2022-12-29T20:04:51.000Z","size":62786,"stargazers_count":66,"open_issues_count":5,"forks_count":9,"subscribers_count":3,"default_branch":"main","last_synced_at":"2023-05-19T05:15:33.762Z","etag":null,"topics":["3d-face","3d-face-modelling","auto-encoder","generative-model","mesh-generation","shape-synthesis","texture-synthesis"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aashishrai3799.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}},"created_at":"2022-06-21T21:04:11.000Z","updated_at":"2023-05-19T03:55:07.000Z","dependencies_parsed_at":"2023-01-31T09:46:04.057Z","dependency_job_id":null,"html_url":"https://github.com/aashishrai3799/3DFaceCAM","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aashishrai3799%2F3DFaceCAM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aashishrai3799%2F3DFaceCAM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aashishrai3799%2F3DFaceCAM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aashishrai3799%2F3DFaceCAM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aashishrai3799","download_url":"https://codeload.github.com/aashishrai3799/3DFaceCAM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225824809,"owners_count":17529906,"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","3d-face-modelling","auto-encoder","generative-model","mesh-generation","shape-synthesis","texture-synthesis"],"created_at":"2024-11-22T00:54:18.741Z","updated_at":"2024-11-22T00:54:20.102Z","avatar_url":"https://github.com/aashishrai3799.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearance\n\nFariborz Teherkhani, Aashish Rai*, Shaunak Srivastava*, Quankai Gao*, Xuanbai Chen, Fernando de la Torre, Steven Song, Aayush Prakash, Daeil Kim (* equal contribution)\n\n### Carnegie Mellon University, Facebook/Meta\n\n### WACV 2023\n\nThis is the official Pytorch implementation of the paper.\n\n\n[[Project Page](https://aashishrai3799.github.io/3DFaceCAM)] [[Video](https://drive.google.com/file/d/1PqIN4Rzp4vapWs2pUegUEoMhg4lM2Smy/view?usp=sharing)] [[Colab Demo](#)] [[Arxiv](https://arxiv.org/abs/2208.14263)] \n\n![](3dfacecam.gif)\n\n![](arch.png)\n\n## Testing\n\nConda environment: Refer environment.yml\n\nDownload pre-trained weights and put the \"checkpoints\" folder in the main directory. [[Link](https://drive.google.com/file/d/1hK31wVAoieRiVFydPxnx0MVpx6AnWN1-/view?usp=sharing)]\n\n- Generate 3D Faces (mesh and texture)\n    ```\n    python generate_faces.py\n    ```\n    \n- Generate meshes only\n    ```\n    python test_gan3d.py\n    ```\n    \n- Generate textures only\n    ```\n    python test_texture.py\n    ```\n\n## Train your own model\n\n### Dataset\n\nWe primarily used the FaceScape dataset. It can be downloaded from [[Link](https://facescape.nju.edu.cn/Page_Download/)]. The dataset is restricted to be used for non-commercial research only. Learn more about Facescape License [[Link](https://facescape.nju.edu.cn/static/License_Agreement.pdf)].\n\n### Preprocess data\n\n    - Download Facescape dataset and specify path to the \"facescape_trainset\" folder.\n    \n    python preprocess_traindata.py\n    \n\n### Start training\n\n- Shape\n    ```\n    Train AE\n    python train_ae.py \n    ```\n    ```\n    Generate Reduced Data\n    python gen_reduced_data.py \n    ```\n    \n    ```\n    Train GAN\n    python train_gan3d.py \n    ```\n\n- Texture\n    ```\n    Train P-GAN\n    python train_texture.py --init_step 1 --batch_size 128\n    ```\n\n## License\n\nThe code is available under X11 License. Please read the license terms available at [[Link](https://github.com/aashishrai3799/3DFaceCAM/blob/main/LICENSE)]. Quick summary available at [[Link](https://www.tldrlegal.com/l/x11)].\n\n## Citation\n\nIf you use find this paper/code useful, please consider citing:\n\n```\n@InProceedings{Taherkhani_2023_WACV,\n    author    = {Taherkhani, Fariborz and Rai, Aashish and Gao, Quankai and Srivastava, Shaunak and Chen, Xuanbai and de la Torre, Fernando and Song, Steven and Prakash, Aayush and Kim, Daeil},\n    title     = {Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearance},\n    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},\n    month     = {January},\n    year      = {2023},\n    pages     = {826-836}\n}\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faashishrai3799%2F3dfacecam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faashishrai3799%2F3dfacecam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faashishrai3799%2F3dfacecam/lists"}