{"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/pad-net-a-perception-aided-single-image","title":"PAD-Net: A Perception-Aided Single Image Dehazing Network","arxiv_id":"1805.03146","date":"2018-05-08","proceeding":null,"authors":["Yu Liu","Guanlong Zhao"],"abstract":"In this work, we investigate the possibility of replacing the $\\ell_2$ loss\nwith perceptually derived loss functions (SSIM, MS-SSIM, etc.) in training an\nend-to-end dehazing neural network. Objective experimental results suggest that\nby merely changing the loss function we can obtain significantly higher PSNR\nand SSIM scores on the SOTS set in the RESIDE dataset, compared with a\nstate-of-the-art end-to-end dehazing neural network (AOD-Net) that uses the\n$\\ell_2$ loss. The best PSNR we obtained was 23.50 (4.2% relative improvement),\nand the best SSIM we obtained was 0.8747 (2.3% relative improvement.)","url_abs":"http://arxiv.org/abs/1805.03146v1","url_pdf":"http://arxiv.org/pdf/1805.03146v1.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":"pad-net-a-perception-aided-single-image","repo_url":"https://github.com/guanlongzhao/single-image-dehazing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"ms-ssim","task_name":"MS-SSIM"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}