{"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/conditional-gans-for-multi-illuminant-color","title":"Conditional GANs for Multi-Illuminant Color Constancy: Revolution or Yet Another Approach?","arxiv_id":"1811.06604","date":"2018-11-15","proceeding":null,"authors":["Oleksii Sidorov"],"abstract":"Non-uniform and multi-illuminant color constancy are important tasks, the\nsolution of which will allow to discard information about lighting conditions\nin the image. Non-uniform illumination and shadows distort colors of real-world\nobjects and mostly do not contain valuable information. Thus, many computer\nvision and image processing techniques would benefit from automatic discarding\nof this information at the pre-processing step. In this work we propose novel\nview on this classical problem via generative end-to-end algorithm based on\nimage conditioned Generative Adversarial Network. We also demonstrate the\npotential of the given approach for joint shadow detection and removal. Forced\nby the lack of training data, we render the largest existing shadow removal\ndataset and make it publicly available. It consists of approximately 6,000\npairs of wide field of view synthetic images with and without shadows.","url_abs":"http://arxiv.org/abs/1811.06604v2","url_pdf":"http://arxiv.org/pdf/1811.06604v2.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":"conditional-gans-for-multi-illuminant-color","repo_url":"https://github.com/acecreamu/angularGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"color-constancy","task_name":"Color Constancy"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"shadow-detection","task_name":"Shadow Detection"},{"task_slug":"shadow-detection-and-removal","task_name":"Shadow Detection And Removal"},{"task_slug":"shadow-removal","task_name":"Shadow Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.06604","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}