{"id":15027775,"url":"https://github.com/kupynorest/deblurgan","last_synced_at":"2025-05-15T10:05:54.387Z","repository":{"id":42234086,"uuid":"89488284","full_name":"KupynOrest/DeblurGAN","owner":"KupynOrest","description":"Image Deblurring using Generative Adversarial Networks","archived":false,"fork":false,"pushed_at":"2019-12-25T18:40:00.000Z","size":87920,"stargazers_count":2591,"open_issues_count":148,"forks_count":528,"subscribers_count":60,"default_branch":"master","last_synced_at":"2025-05-15T10:04:54.642Z","etag":null,"topics":["blurry-images","computer-vision","convolutional-networks","convolutional-neural-networks","deblurring","deep-learning","gan","image-manipulation","image-processing","image-to-image-translation","neural-network","paper","pix2pix","pytorch"],"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/KupynOrest.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":"2017-04-26T14:08:11.000Z","updated_at":"2025-05-15T00:56:25.000Z","dependencies_parsed_at":"2022-08-12T09:51:13.979Z","dependency_job_id":null,"html_url":"https://github.com/KupynOrest/DeblurGAN","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/KupynOrest%2FDeblurGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KupynOrest%2FDeblurGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KupynOrest%2FDeblurGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KupynOrest%2FDeblurGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KupynOrest","download_url":"https://codeload.github.com/KupynOrest/DeblurGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254319720,"owners_count":22051073,"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":["blurry-images","computer-vision","convolutional-networks","convolutional-neural-networks","deblurring","deep-learning","gan","image-manipulation","image-processing","image-to-image-translation","neural-network","paper","pix2pix","pytorch"],"created_at":"2024-09-24T20:07:01.723Z","updated_at":"2025-05-15T10:05:49.321Z","avatar_url":"https://github.com/KupynOrest.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DeblurGAN\n[arXiv Paper Version](https://arxiv.org/pdf/1711.07064.pdf)\n\nPytorch implementation of the paper DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks.\n\nOur network takes blurry image as an input and procude the corresponding sharp estimate, as in the example:\n\u003cimg src=\"images/animation3.gif\" width=\"400px\"/\u003e \u003cimg src=\"images/animation4.gif\" width=\"400px\"/\u003e\n\n\nThe model we use is Conditional Wasserstein GAN with Gradient Penalty + Perceptual loss based on VGG-19 activations. Such architecture also gives good results on other image-to-image translation problems (super resolution, colorization, inpainting, dehazing etc.)\n\n## How to run\n\n### Prerequisites\n- NVIDIA GPU + CUDA CuDNN (CPU untested, feedback appreciated)\n- Pytorch\n\nDownload weights from [Google Drive](https://drive.google.com/file/d/1liKzdjMRHZ-i5MWhC72EL7UZLNPj5_8Y/view?usp=sharing) . Note that during the inference you need to keep only Generator weights.\n\nPut the weights into \n```bash\n/.checkpoints/experiment_name\n```\nTo test a model put your blurry images into a folder and run:\n```bash\npython test.py --dataroot /.path_to_your_data --model test --dataset_mode single --learn_residual\n```\n## Data\nDownload dataset for Object Detection benchmark from [Google Drive](https://drive.google.com/file/d/1CPMBmRj-jBDO2ax4CxkBs9iczIFrs8VA/view?usp=sharing)\n\n## Train\n\nIf you want to train the model on your data run the following command to create image pairs:\n```bash\npython datasets/combine_A_and_B.py --fold_A /path/to/data/A --fold_B /path/to/data/B --fold_AB /path/to/data\n```\nAnd then the following command to train the model\n\n```bash\npython train.py --dataroot /.path_to_your_data --learn_residual --resize_or_crop crop --fineSize CROP_SIZE (we used 256)\n```\n\n## Other Implementations\n\n[Keras Blog](https://blog.sicara.com/keras-generative-adversarial-networks-image-deblurring-45e3ab6977b5)\n\n[Keras Repository](https://github.com/RaphaelMeudec/deblur-gan)\n\n\n\n## Citation\n\nIf you find our code helpful in your research or work please cite our paper.\n\n```\n@article{DeblurGAN,\n  title = {DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks},\n  author = {Kupyn, Orest and Budzan, Volodymyr and Mykhailych, Mykola and Mishkin, Dmytro and Matas, Jiri},\n  journal = {ArXiv e-prints},\n  eprint = {1711.07064},\n  year = 2017\n}\n```\n\n## Acknowledgments\nCode borrows heavily from [pix2pix](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix). The images were taken from GoPRO test dataset - [DeepDeblur](https://github.com/SeungjunNah/DeepDeblur_release)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkupynorest%2Fdeblurgan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkupynorest%2Fdeblurgan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkupynorest%2Fdeblurgan/lists"}