{"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/single-image-dehazing-using-color-ellipsoid","title":"Single Image Dehazing Using Color Ellipsoid Prior","arxiv_id":null,"date":"2018-02-01","proceeding":"IEEE Transactions on Image Processing 2018 2","authors":["Trung Minh Bui","Student Member","and Wonha Kim","Senior Member","IEEE"],"abstract":"In this paper, we propose a new single-image dehazing\r\nmethod. The proposed method constructs color ellipsoids that\r\nare statistically fitted to haze pixel clusters in RGB space and\r\nthen calculates the transmission values through color ellipsoid\r\ngeometry. The transmission values generated by the proposed\r\nmethod maximize the contrast of dehazed pixels, while preventing\r\nover-saturated pixels. The values are also statistically robust\r\nbecause they are calculated from the averages of the haze pixel\r\nvalues. Furthermore, rather than apply a highly complex refinement\r\nprocess to reduce halo or unnatural artifacts, we embed\r\na fuzzy segmentation process into the construction of the color\r\nellipsoid so that the proposed method simultaneously executes\r\nthe transmission calculation and the refinement process. The\r\nresults of an experimental performance evaluation verify that\r\ncompared with prevailing dehazing methods the proposed method\r\nperforms effectively across a wide range of haze and noise levels\r\nwithout causing any visible artifacts. Moreover, the relatively low\r\ncomplexity of the proposed method will facilitate its real-time\r\napplications.","url_abs":"https://ieeexplore.ieee.org/document/8101508","url_pdf":"https://github.com/mtbui2010/CEP/blob/master/single%20image%20dehazing%20using%20color%20ellipsoid%20prior.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":"single-image-dehazing-using-color-ellipsoid","repo_url":"https://github.com/mtbui2010/CEP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}