{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/crafting-a-toolchain-for-image-restoration-by","title":"Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning","arxiv_id":"1804.03312","date":"2018-04-10","proceeding":"CVPR 2018 6","authors":["Ke Yu","Chao Dong","Liang Lin","Chen Change Loy"],"abstract":"We investigate a novel approach for image restoration by reinforcement\nlearning. Unlike existing studies that mostly train a single large network for\na specialized task, we prepare a toolbox consisting of small-scale\nconvolutional networks of different complexities and specialized in different\ntasks. Our method, RL-Restore, then learns a policy to select appropriate tools\nfrom the toolbox to progressively restore the quality of a corrupted image. We\nformulate a step-wise reward function proportional to how well the image is\nrestored at each step to learn the action policy. We also devise a joint\nlearning scheme to train the agent and tools for better performance in handling\nuncertainty. In comparison to conventional human-designed networks, RL-Restore\nis capable of restoring images corrupted with complex and unknown distortions\nin a more parameter-efficient manner using the dynamically formed toolchain.","url_abs":"http://arxiv.org/abs/1804.03312v1","url_pdf":"http://arxiv.org/pdf/1804.03312v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"crafting-a-toolchain-for-image-restoration-by","repo_url":"https://github.com/sg-nm/Operation-wise-attention-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"crafting-a-toolchain-for-image-restoration-by","repo_url":"https://github.com/yuke93/RL-Restore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03312","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}