{"id":18614290,"url":"https://github.com/minar09/acgpn","last_synced_at":"2025-04-11T00:30:30.969Z","repository":{"id":40240365,"uuid":"296566265","full_name":"minar09/ACGPN","owner":"minar09","description":"\"Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content\"，CVPR 2020. (Modified from original with fixes for inference)","archived":false,"fork":false,"pushed_at":"2023-12-22T05:03:41.000Z","size":227,"stargazers_count":80,"open_issues_count":17,"forks_count":72,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-25T06:51:15.127Z","etag":null,"topics":["2020","acgpn","cvpr","virtual-try-on","virtual-tryon","viton","vton"],"latest_commit_sha":null,"homepage":"https://github.com/switchablenorms/DeepFashion_Try_On","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/minar09.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":"2020-09-18T08:48:50.000Z","updated_at":"2025-03-25T04:39:48.000Z","dependencies_parsed_at":"2024-11-07T03:40:17.701Z","dependency_job_id":null,"html_url":"https://github.com/minar09/ACGPN","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/minar09%2FACGPN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FACGPN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FACGPN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FACGPN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/minar09","download_url":"https://codeload.github.com/minar09/ACGPN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248322201,"owners_count":21084333,"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":["2020","acgpn","cvpr","virtual-try-on","virtual-tryon","viton","vton"],"created_at":"2024-11-07T03:25:52.599Z","updated_at":"2025-04-11T00:30:30.960Z","avatar_url":"https://github.com/minar09.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Disclaimer\nThis is just a slightly modified repository of [DeepFashion_Try_On (ACGPN)](https://github.com/switchablenorms/DeepFashion_Try_On) for inference and visualization. Please refer to the original repository for details.\n\n# Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content, CVPR'20.\nCopy of the Official code for CVPR 2020 paper 'Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content'.\nWe rearranged the VITON dataset for easy access.\n\n[[Dataset Partition Label]](https://drive.google.com/open?id=1Jt9DykVUmUo5dzzwyi4C_1wmWgVYsFDl)  [[Sample Try-on Video]](https://www.youtube.com/watch?v=BbKBSfDBcxI) [[Checkpoints]](https://drive.google.com/file/d/1UWT6esQIU_d4tUm8cjxDKMhB8joQbrFx/view?usp=sharing) \n\n[[Dataset_Test]](https://drive.google.com/file/d/1tE7hcVFm8Td8kRh5iYRBSDFdvZIkbUIR/view?usp=sharing) [[Dataset_Train]](https://drive.google.com/file/d/1lHNujZIq6KVeGOOdwnOXVCSR5E7Kv6xv/view?usp=sharing)\n\n\n[[Paper]](https://arxiv.org/abs/2003.05863)\n\n## Inference\n1) Download the test dataset and unzip\n2) Download the checkpoints and unzip\n3) Then run - ```python test.py```\n\n**Dataset Partition** We present a criterion to introduce the difficulty of try-on for a certain reference image.\n## The specific key points we choose to evaluate the try-on difficulty\n![image](https://github.com/switchablenorms/DeepFashion_Try_On/blob/master/images/criterion.png)\n\nWe use the pose map to calculate the difficulty level of try-on. The key motivation behind this is the more complex the occlusions and layouts are in the clothing area, the harder it will be. And the formula is given,\n## The formula to compute the difficulty of try-onreference image\n\n![image](https://github.com/switchablenorms/DeepFashion_Try_On/blob/master/images/formula.png)\n\nwhere t is a certain key point, Mp' is the set of key point we take into consideration, and N is the size of the set. \n## Segmentation Label\n```bash\n0 -\u003e Background\n1 -\u003e Hair\n4 -\u003e Upclothes\n5 -\u003e Left-shoe \n6 -\u003e Right-shoe\n7 -\u003e Noise\n8 -\u003e Pants\n9 -\u003e Left_leg\n10 -\u003e Right_leg\n11 -\u003e Left_arm\n12 -\u003e Face\n13 -\u003e Right_arm\n```\n## Sample images from different difficulty level\n\n![image](https://github.com/switchablenorms/DeepFashion_Try_On/blob/master/images/difficulty.png)\n\n## Sample Try-on Results\n  \n![image](https://github.com/switchablenorms/DeepFashion_Try_On/blob/master/images/tryon.png)\n\n## Training Details\nFor better inference performance, model G and G2 should be trained with 200 epoches, while model G1 and U net should be trained with 20 epoches.\n\n## License\nThe use of this software is RESTRICTED to **non-commercial research and educational purposes**.\n\n## Citation\nIf you use our code or models in your research, please cite with:\n```\n@InProceedings{Yang_2020_CVPR,\nauthor = {Yang, Han and Zhang, Ruimao and Guo, Xiaobao and Liu, Wei and Zuo, Wangmeng and Luo, Ping},\ntitle = {Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image Content},\nbooktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\nmonth = {June},\nyear = {2020}\n}\n```\n\n## Dataset\n**VITON Dataset** This dataset is presented in [VITON](https://github.com/xthan/VITON), containing 19,000 image pairs, each of which includes a front-view woman image and a top clothing image. After removing the invalid image pairs, it yields 16,253 pairs, further splitting into a training set of 14,221 paris and a testing set of 2,032 pairs.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminar09%2Facgpn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fminar09%2Facgpn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminar09%2Facgpn/lists"}