{"id":13719509,"url":"https://github.com/switchablenorms/CelebAMask-HQ","last_synced_at":"2025-05-07T11:32:16.324Z","repository":{"id":34509376,"uuid":"178800521","full_name":"switchablenorms/CelebAMask-HQ","owner":"switchablenorms","description":"A large-scale face dataset for face parsing, recognition, generation and editing.","archived":false,"fork":false,"pushed_at":"2024-06-20T04:33:41.000Z","size":43513,"stargazers_count":2120,"open_issues_count":58,"forks_count":352,"subscribers_count":47,"default_branch":"master","last_synced_at":"2024-11-11T17:26:44.772Z","etag":null,"topics":["celeba","face-generation","face-recognition","face-segmentation","generative-adversarial-network"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/switchablenorms.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2019-04-01T06:35:34.000Z","updated_at":"2024-11-11T06:44:08.000Z","dependencies_parsed_at":"2024-10-15T01:41:09.996Z","dependency_job_id":"6ce19b4f-0653-46d6-bacd-665a2195a514","html_url":"https://github.com/switchablenorms/CelebAMask-HQ","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/switchablenorms%2FCelebAMask-HQ","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/switchablenorms%2FCelebAMask-HQ/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/switchablenorms%2FCelebAMask-HQ/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/switchablenorms%2FCelebAMask-HQ/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/switchablenorms","download_url":"https://codeload.github.com/switchablenorms/CelebAMask-HQ/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224596940,"owners_count":17337814,"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":["celeba","face-generation","face-recognition","face-segmentation","generative-adversarial-network"],"created_at":"2024-08-03T01:00:50.386Z","updated_at":"2024-11-14T09:30:22.911Z","avatar_url":"https://github.com/switchablenorms.png","language":"Python","funding_links":[],"categories":["Datasets","人像\\姿势\\3D人脸","Uncategorized"],"sub_categories":["Faces/People (restricted licenses)","Face Video Restoration","网络服务_其他","Uncategorized"],"readme":"# CelebAMask-HQ\n\n[[Paper]](https://arxiv.org/abs/1907.11922) [[Demo]](https://www.youtube.com/watch?v=T1o38DFalWs)  \n\n![image](https://github.com/switchablenorms/CelebAMask-HQ/blob/master/images/front.jpeg)\n\n**CelebAMask-HQ** is a large-scale face image dataset that has **30,000** high-resolution face images selected from the CelebA dataset by following CelebA-HQ. Each image has segmentation mask of facial attributes corresponding to CelebA.\n\nThe masks of CelebAMask-HQ were manually-annotated with the size of **512 x 512** and **19 classes** including all facial components and accessories such as skin, nose, eyes, eyebrows, ears, mouth, lip, hair, hat, eyeglass, earring, necklace, neck, and cloth. \n\nCelebAMask-HQ can be used to **train and evaluate algorithms of face parsing, face recognition, and GANs for face generation and editing**.\n\n* If you need the identity labels and the attribute labels of the images, please send request to the [CelebA team](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html).\n\n* Demo of interactive facial image manipulation\n\n![image](https://github.com/switchablenorms/CelebAMask-HQ/blob/master/images/demo.gif)\n\n## Sample Images\n\n![image](https://github.com/switchablenorms/CelebAMask-HQ/blob/master/images/sample.png)\n\n## Face Manipulation Model with CelebAMask-HQ\nCelebAMask-HQ can be used on several research fields including: facial image manipulation, face parsing, face recognition, and face hallucination. We showcase an application on interactive facial image manipulation as bellow:\n\n* Samples of interactive facial image manipulation\n\n![image](https://github.com/switchablenorms/CelebAMask-HQ/blob/master/images/sample_interactive.png)\n\n## CelebAMask-HQ Dataset Downloads\n* Google Drive: [downloading link](https://drive.google.com/open?id=1badu11NqxGf6qM3PTTooQDJvQbejgbTv)\n* Baidu Drive: [downloading link](https://pan.baidu.com/s/1wN1E-B1bJ7mE1mrn9loj5g)\n\n## Related Works\n* **CelebA** dataset:\u003cbr/\u003e\nZiwei Liu, Ping Luo, Xiaogang Wang and Xiaoou Tang, \"Deep Learning Face Attributes in the Wild\", in IEEE International Conference on Computer Vision (ICCV), 2015 \n* **CelebA-HQ** was collected from CelebA and further post-processed by the following paper :\u003cbr/\u003e\nKarras et. al, \"Progressive Growing of GANs for Improved Quality, Stability, and Variation\", in Internation Conference on Reoresentation Learning (ICLR), 2018\n\n## Dataset Agreement\n* The CelebAMask-HQ dataset is available for **non-commercial research purposes** only.\n* You agree **not to** reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purposes, any portion of the images and any portion of derived data.\n* You agree **not to** further copy, publish or distribute any portion of the CelebAMask-HQ dataset. Except, for internal use at a single site within the same organization it is allowed to make copies of the dataset.\n\n## Related Projects using CelebAMask-HQ\n* [SPADE-TensorFlow](https://github.com/taki0112/SPADE-Tensorflow)\n* [FaceParsing-PyTorch](https://github.com/zllrunning/face-parsing.PyTorch)\n\n## License and Citation\nThe use of this software is RESTRICTED to **non-commercial research and educational purposes**.\n```\n@inproceedings{CelebAMask-HQ,\n  title={MaskGAN: Towards Diverse and Interactive Facial Image Manipulation},\n  author={Lee, Cheng-Han and Liu, Ziwei and Wu, Lingyun and Luo, Ping},\n  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswitchablenorms%2FCelebAMask-HQ","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fswitchablenorms%2FCelebAMask-HQ","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fswitchablenorms%2FCelebAMask-HQ/lists"}