{"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/i-haze-a-dehazing-benchmark-with-real-hazy","title":"I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images","arxiv_id":"1804.05091","date":"2018-04-13","proceeding":null,"authors":["Codruta O. Ancuti","Cosmin Ancuti","Radu Timofte","Christophe De Vleeschouwer"],"abstract":"Image dehazing has become an important computational imaging topic in the\nrecent years. However, due to the lack of ground truth images, the comparison\nof dehazing methods is not straightforward, nor objective. To overcome this\nissue we introduce a new dataset -named I-HAZE- that contains 35 image pairs of\nhazy and corresponding haze-free (ground-truth) indoor images. Different from\nmost of the existing dehazing databases, hazy images have been generated using\nreal haze produced by a professional haze machine. For easy color calibration\nand improved assessment of dehazing algorithms, each scene include a MacBeth\ncolor checker. Moreover, since the images are captured in a controlled\nenvironment, both haze-free and hazy images are captured under the same\nillumination conditions. This represents an important advantage of the I-HAZE\ndataset that allows us to objectively compare the existing image dehazing\ntechniques using traditional image quality metrics such as PSNR and SSIM.","url_abs":"http://arxiv.org/abs/1804.05091v1","url_pdf":"http://arxiv.org/pdf/1804.05091v1.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":"i-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"}},{"paper_slug":"i-haze-a-dehazing-benchmark-with-real-hazy","repo_url":"https://github.com/v1t0ry/OTM-AAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[],"datasets_introduced":[{"slug":"i-haze-1","name":"I-HAZE","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05091","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}