{"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/real-world-underwater-enhancement-challenges","title":"Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions","arxiv_id":"1901.05320","date":"2019-01-15","proceeding":null,"authors":["Risheng Liu","Xin Fan","Ming Zhu","Minjun Hou","Zhongxuan Luo"],"abstract":"Underwater image enhancement is such an important low-level vision task with\nmany applications that numerous algorithms have been proposed in recent years.\nThese algorithms developed upon various assumptions demonstrate successes from\nvarious aspects using different data sets and different metrics. In this work,\nwe setup an undersea image capturing system, and construct a large-scale\nReal-world Underwater Image Enhancement (RUIE) data set divided into three\nsubsets. The three subsets target at three challenging aspects for enhancement,\ni.e., image visibility quality, color casts, and higher-level\ndetection/classification, respectively. We conduct extensive and systematic\nexperiments on RUIE to evaluate the effectiveness and limitations of various\nalgorithms to enhance visibility and correct color casts on images with\nhierarchical categories of degradation. Moreover, underwater image enhancement\nin practice usually serves as a preprocessing step for mid-level and high-level\nvision tasks. We thus exploit the object detection performance on enhanced\nimages as a brand new task-specific evaluation criterion. The findings from\nthese evaluations not only confirm what is commonly believed, but also suggest\npromising solutions and new directions for visibility enhancement, color\ncorrection, and object detection on real-world underwater images.","url_abs":"http://arxiv.org/abs/1901.05320v2","url_pdf":"http://arxiv.org/pdf/1901.05320v2.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":"real-world-underwater-enhancement-challenges","repo_url":"https://github.com/dlut-dimt/Realworld-Underwater-Image-Enhancement-RUIE-Benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.05320","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}