{"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/o-haze-a-dehazing-benchmark-with-real-hazy","title":"O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images","arxiv_id":"1804.05101","date":"2018-04-13","proceeding":null,"authors":["Codruta O. Ancuti","Cosmin Ancuti","Radu Timofte","Christophe De Vleeschouwer"],"abstract":"Haze removal or dehazing is a challenging ill-posed problem that has drawn a\nsignificant attention in the last few years. Despite this growing interest, the\nscientific community is still lacking a reference dataset to evaluate\nobjectively and quantitatively the performance of proposed dehazing methods.\nThe few datasets that are currently considered, both for assessment and\ntraining of learning-based dehazing techniques, exclusively rely on synthetic\nhazy images. To address this limitation, we introduce the first outdoor scenes\ndatabase (named O-HAZE) composed of pairs of real hazy and corresponding\nhaze-free images. In practice, hazy images have been captured in presence of\nreal haze, generated by professional haze machines, and OHAZE contains 45\ndifferent outdoor scenes depicting the same visual content recorded in\nhaze-free and hazy conditions, under the same illumination parameters. To\nillustrate its usefulness, O-HAZE is used to compare a representative set of\nstate-of-the-art dehazing techniques, using traditional image quality metrics\nsuch as PSNR, SSIM and CIEDE2000. This reveals the limitations of current\ntechniques, and questions some of their underlying assumptions.","url_abs":"http://arxiv.org/abs/1804.05101v1","url_pdf":"http://arxiv.org/pdf/1804.05101v1.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":"o-haze-a-dehazing-benchmark-with-real-hazy","repo_url":"https://github.com/inyong37/Vision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"ssim","task_name":"SSIM"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05101","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}