{"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/convolutional-color-constancy","title":"Convolutional Color Constancy","arxiv_id":"1507.00410","date":"2015-07-02","proceeding":"ICCV 2015 12","authors":["Jonathan T. Barron"],"abstract":"Color constancy is the problem of inferring the color of the light that\nilluminated a scene, usually so that the illumination color can be removed.\nBecause this problem is underconstrained, it is often solved by modeling the\nstatistical regularities of the colors of natural objects and illumination. In\ncontrast, in this paper we reformulate the problem of color constancy as a 2D\nspatial localization task in a log-chrominance space, thereby allowing us to\napply techniques from object detection and structured prediction to the color\nconstancy problem. By directly learning how to discriminate between correctly\nwhite-balanced images and poorly white-balanced images, our model is able to\nimprove performance on standard benchmarks by nearly 40%.","url_abs":"http://arxiv.org/abs/1507.00410v2","url_pdf":"http://arxiv.org/pdf/1507.00410v2.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":"convolutional-color-constancy","repo_url":"https://github.com/leggedrobotics/raw_image_pipeline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"color-constancy","task_name":"Color Constancy"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.00410","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}