{"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/self-refining-deep-symmetry-enhanced-network","title":"Self-Refining Deep Symmetry Enhanced Network for Rain Removal","arxiv_id":"1811.04761","date":"2018-11-06","proceeding":null,"authors":["Hanrong Ye","Xia Li","Hong Liu","Wei Shi","Mengyuan Liu","Qianru Sun"],"abstract":"Rain removal aims to extract and remove rain streaks from images. Although\nconvolutional neural network (CNN) based methods have achieved impressive\nresults in this field, they are not equivariant to object rotation, which\ndecreases their generalization capacity for tilted rain streaks. In order to\nsolve this problem, we propose Deep Symmetry Enhanced Network (DSEN). DSEN\nextracts rotationally equivariant features of rain streaks, and then generates\nrain layer for image restoration. Furthermore, an efficient self-refining\nmechanism is designed to remove tilted rain streaks more thoroughly.\nExperimental study verifies the validity of our method, with self-refining DSEN\nyielding the state-of-the-art performance on both synthetic and real-world rain\nimage datasets.","url_abs":"http://arxiv.org/abs/1811.04761v1","url_pdf":"http://arxiv.org/pdf/1811.04761v1.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":"self-refining-deep-symmetry-enhanced-network","repo_url":"https://github.com/prismformore/SDSEN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"rain-removal","task_name":"Rain Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}