{"id":13577369,"url":"https://github.com/jammer345/SL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning","last_synced_at":"2025-04-05T11:32:42.564Z","repository":{"id":201511371,"uuid":"458760284","full_name":"jammer345/SL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning","owner":"jammer345","description":"SL-CycleGAN: Blind Motion Deblurring in Cycles using Sparse Learning","archived":false,"fork":false,"pushed_at":"2024-09-01T06:26:22.000Z","size":18537,"stargazers_count":9,"open_issues_count":2,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-05T14:44:54.010Z","etag":null,"topics":["computer-vision","deblurring","generative-adversarial-network","image-processing","sparse","state-of-the-art"],"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/jammer345.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}},"created_at":"2022-02-13T09:11:44.000Z","updated_at":"2024-09-01T06:26:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"cbbd2a18-241b-4ac6-bcbc-c2b509bac933","html_url":"https://github.com/jammer345/SL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning","commit_stats":null,"previous_names":["jammer345/sl-cyclegan-blind-motion-deblurring-in-cycles-using-sparse-learning"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jammer345","download_url":"https://codeload.github.com/jammer345/SL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247331684,"owners_count":20921843,"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":["computer-vision","deblurring","generative-adversarial-network","image-processing","sparse","state-of-the-art"],"created_at":"2024-08-01T15:01:20.885Z","updated_at":"2025-04-05T11:32:42.038Z","avatar_url":"https://github.com/jammer345.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# SL-CycleGAN: Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning (2022)\n[![arXiv Prepring](https://img.shields.io/badge/arXiv-Preprint-lightgrey?logo=arxiv)](https://arxiv.org/abs/2111.04026)\n \n Ali Syed Saqlain\u003csup\u003e1\u003c/sup\u003e, Li Yun Wang\u003csup\u003e2\u003c/sup\u003e, \u0026 Fang Fang\u003csup\u003e1\u003c/sup\u003e\n \u003cbr/\u003e\n \u003csup\u003e1 \u003c/sup\u003eNorth China Electric Power University, Beijing\n \u003cbr/\u003e\n \u003csup\u003e2 \u003c/sup\u003ePortland State University, USA\n \n## Abstract\nIn this paper, we introduce an end-to-end generative adversarial network (GAN) based on sparse learning for single image motion deblurring, which we called SL-CycleGAN. For the first time in image motion deblurring, we propose a sparse ResNet-block as a combination of sparse convolution layers and a trainable spatial pooler k-winner based on HTM (Hierarchical Temporal Memory) to replace non-linearity such as ReLU in the ResNet-block of SL-CycleGAN generators. Furthermore, we take our inspiration from the domain-to-domain translation ability of the CycleGAN, and we show that image deblurring can be cycle-consistent while achieving the best qualitative results. Finally, we perform extensive experiments on popular image benchmarks both qualitatively and quantitatively and achieve the highest PSNR of 38.087 dB on GoPro dataset, which is 5.377 dB better than the most recent deblurring method.\n## Network Architecture \n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/arc.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n## Results\n\n### GoPro Dataset \n\nDeblurring results on GoPro test images\n\nThe results shown in Tab I of SL-CycleGAN are conducted on 256x256.\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/GoPro.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/GoPro_eval.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n\n\n### Kohler Dataset\n\nDeblurring results on Kohler test images using pre-trained model\n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/Kohler.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/Kohler_eval.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n### Lai Dataset\n\nDeblurring results on Lai test images via pre-trained model \n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/Lai.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n### Test images from Pan et al \n\nBlind deblurring results on images from (Pan et al.) via pre-trained model. The GT images weren't fed to the network only the blurry inputs \n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/Pan.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n### Deblurring Neptune's satellite Triton \n\nTest images \n\n\u003cp align=\"center\"\u003e\u003cimg width=\"100%\" src=\"imgs/Triton.png\" style=\"background-color:white;\" /\u003e\u003c/p\u003e\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjammer345%2FSL-CycleGAN-Blind-Motion-Deblurring-in-Cycles-using-Sparse-Learning/lists"}