{"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/an-improved-air-light-estimation-scheme-for","title":"An Improved Air-Light Estimation Scheme for Single Haze Images Using Color Constancy Prior","arxiv_id":null,"date":"2020-09-21","proceeding":null,"authors":["Sidharth Gautam","Tapan Kumar Gandhi","B.K. Panigrahi"],"abstract":"Hazy environment attenuates the scene radiance and\r\ncauses difficulty in distinguishing the color and texture of the scene.\r\nA crucial step in dehazing is the recovery of the global air-light\r\nvector. Traditional methods usually interpret the RGB value of\r\nthe brightest region in haze images as the air-light. In this letter,\r\na new prior called ‘color constancy prior’ has been proposed to\r\nimprove the robustness of air-light estimation when varicolored\r\nillumination exists.The prior utilizes the statistical observation that\r\ndistant scenery objects become the most haze-opaque due to the\r\npixel escalation towards the higher intensity side. The comparative\r\nevaluation on a variety of haze images manifests that the proposed\r\nprior perform better than existing air-light recovery methods and\r\ncan be used for subsequent dehazing applications.","url_abs":"https://ieeexplore.ieee.org/document/9201388","url_pdf":"https://ieeexplore.ieee.org/document/9201388","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":"an-improved-air-light-estimation-scheme-for","repo_url":"https://github.com/sidharthscorpio/color-constancy-prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"color-constancy","task_name":"Color Constancy"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/single-image-dehazing-on-uieb","task":"Single Image Dehazing","dataset":"UIEB","model":"Bradley-Terry model","rank_in_archive_order":1,"of":1,"metrics":{"L2 Norm":"minimum is better"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}