{"id":13536639,"url":"https://github.com/VITA-Group/EnlightenGAN","last_synced_at":"2025-04-02T03:31:00.043Z","repository":{"id":38338869,"uuid":"192192752","full_name":"VITA-Group/EnlightenGAN","owner":"VITA-Group","description":"[IEEE TIP] \"EnlightenGAN: Deep Light Enhancement without Paired Supervision\" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang","archived":false,"fork":false,"pushed_at":"2024-04-25T07:46:42.000Z","size":18290,"stargazers_count":900,"open_issues_count":15,"forks_count":198,"subscribers_count":20,"default_branch":"master","last_synced_at":"2024-08-11T17:09:20.472Z","etag":null,"topics":["gan","generative-adversarial-networks","low-light","low-light-enhance","pytorch","unsupervised-learning"],"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/VITA-Group.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":"2019-06-16T13:14:30.000Z","updated_at":"2024-08-02T23:54:04.000Z","dependencies_parsed_at":"2023-01-29T08:15:39.464Z","dependency_job_id":"6ab2d567-7fe0-4957-85d3-65383af24024","html_url":"https://github.com/VITA-Group/EnlightenGAN","commit_stats":{"total_commits":51,"total_committers":4,"mean_commits":12.75,"dds":0.4117647058823529,"last_synced_commit":"3e0ba763e23b74c479ee88822d93389a9d2cf635"},"previous_names":["tamu-vita/enlightengan"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FEnlightenGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FEnlightenGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FEnlightenGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VITA-Group%2FEnlightenGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VITA-Group","download_url":"https://codeload.github.com/VITA-Group/EnlightenGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246750944,"owners_count":20827805,"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":["gan","generative-adversarial-networks","low-light","low-light-enhance","pytorch","unsupervised-learning"],"created_at":"2024-08-01T09:00:46.095Z","updated_at":"2025-04-02T03:30:55.467Z","avatar_url":"https://github.com/VITA-Group.png","language":"Python","funding_links":[],"categories":["Python","Methods"],"sub_categories":["Learning-based methods"],"readme":"# EnlightenGAN: Deep Light Enhancement without Paired Supervision\n[Yifan Jiang](https://yifanjiang19.github.io/), Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang\n\n[[Paper]](https://arxiv.org/abs/1906.06972) [[Supplementary Materials]](https://yifanjiang.net/files/EnlightenGAN_Supplementary.pdf)\n\n\n### Representitive Results\n![representive_results](/assets/show_3.png)\n\n### Overal Architecture\n![architecture](/assets/arch.png)\n\n## Environment Preparing\n```\npython3.5\n```\nYou should prepare at least 3 1080ti gpus or change the batch size. \n\n\n```pip install -r requirement.txt``` \u003c/br\u003e\n```mkdir model``` \u003c/br\u003e\nDownload VGG pretrained model from [[Google Drive 1]](https://drive.google.com/file/d/1IfCeihmPqGWJ0KHmH-mTMi_pn3z3Zo-P/view?usp=sharing), and then put it into the directory `model`.\n\n### Training process\nBefore starting training process, you should launch the `visdom.server` for visualizing.\n\n```nohup python -m visdom.server -port=8097```\n\nthen run the following command\n\n```python scripts/script.py --train```\n\n### Testing process\n\nDownload [pretrained model](https://drive.google.com/file/d/1AkV-n2MdyfuZTFvcon8Z4leyVb0i7x63/view?usp=sharing) and put it into `./checkpoints/enlightening`\n\nCreate directories `../test_dataset/testA` and `../test_dataset/testB`. Put your test images on `../test_dataset/testA` (And you should keep whatever one image in `../test_dataset/testB` to make sure program can start.)\n\nRun\n\n```python scripts/script.py --predict ```\n\n### Dataset preparing\n\nTraining data [[Google Drive]](https://drive.google.com/drive/folders/1KivxOm79VidSJnJrMV9osr751UD68pCu?usp=sharing) (unpaired images collected from multiple datasets)\n\nTesting data [[Google Drive]](https://drive.google.com/drive/folders/1PrvL8jShZ7zj2IC3fVdDxBY1oJR72iDf?usp=sharing) (including LIME, MEF, NPE, VV, DICP)\n\nAnd [[BaiduYun]](https://github.com/TAMU-VITA/EnlightenGAN/issues/28) is available now thanks to @YHLelaine!\n\n### Faster Inference\nhttps://github.com/arsenyinfo/EnlightenGAN-inference from @arsenyinfo\n\n\n\nIf you find this work useful for you, please cite\n```\n@article{jiang2021enlightengan,\n  title={Enlightengan: Deep light enhancement without paired supervision},\n  author={Jiang, Yifan and Gong, Xinyu and Liu, Ding and Cheng, Yu and Fang, Chen and Shen, Xiaohui and Yang, Jianchao and Zhou, Pan and Wang, Zhangyang},\n  journal={IEEE Transactions on Image Processing},\n  volume={30},\n  pages={2340--2349},\n  year={2021},\n  publisher={IEEE}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FVITA-Group%2FEnlightenGAN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FVITA-Group%2FEnlightenGAN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FVITA-Group%2FEnlightenGAN/lists"}