{"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/fastderain-a-novel-video-rain-streak-removal","title":"FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors","arxiv_id":"1803.07487","date":"2018-03-20","proceeding":null,"authors":["Tai-Xiang Jiang","Ting-Zhu Huang","Xi-Le Zhao","Liang-Jian Deng","Yao Wang"],"abstract":"Rain streak removal is an important issue in outdoor vision systems and has\nrecently been investigated extensively. In this paper, we propose a novel video\nrain streak removal approach FastDeRain, which fully considers the\ndiscriminative characteristics of rain streaks and the clean video in the\ngradient domain. Specifically, on the one hand, rain streaks are sparse and\nsmooth along the direction of the raindrops, whereas on the other hand, clean\nvideos exhibit piecewise smoothness along the rain-perpendicular direction and\ncontinuity along the temporal direction. Theses smoothness and continuity\nresults in the sparse distribution in the different directional gradient\ndomain, respectively. Thus, we minimize 1) the $\\ell_1$ norm to enhance the\nsparsity of the underlying rain streaks, 2) two $\\ell_1$ norm of unidirectional\nTotal Variation (TV) regularizers to guarantee the anisotropic spatial\nsmoothness, and 3) an $\\ell_1$ norm of the time-directional difference operator\nto characterize the temporal continuity. A split augmented Lagrangian shrinkage\nalgorithm (SALSA) based algorithm is designed to solve the proposed\nminimization model. Experiments conducted on synthetic and real data\ndemonstrate the effectiveness and efficiency of the proposed method. According\nto comprehensive quantitative performance measures, our approach outperforms\nother state-of-the-art methods especially on account of the running time. The\ncode of FastDeRain can be downloaded at\nhttps://github.com/TaiXiangJiang/FastDeRain.","url_abs":"http://arxiv.org/abs/1803.07487v3","url_pdf":"http://arxiv.org/pdf/1803.07487v3.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":"fastderain-a-novel-video-rain-streak-removal","repo_url":"https://github.com/TaiXiangJiang/FastDeRain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fastderain-a-novel-video-rain-streak-removal","repo_url":"https://github.com/uestctensorgroup/FastDeRain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fastderain-a-novel-video-rain-streak-removal","repo_url":"https://github.com/zhaoxile/FastDeRain_-A-Novel-Video-Rain-Streak-Removal-Method-Using-Directional-Gradient-Priors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.07487","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}