{"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/gated-fusion-network-for-single-image","title":"Gated Fusion Network for Single Image Dehazing","arxiv_id":"1804.00213","date":"2018-03-31","proceeding":"CVPR 2018 6","authors":["Wenqi Ren","Lin Ma","Jiawei Zhang","Jinshan Pan","Xiaochun Cao","Wei Liu","Ming-Hsuan Yang"],"abstract":"In this paper, we propose an efficient algorithm to directly restore a clear\nimage from a hazy input. The proposed algorithm hinges on an end-to-end\ntrainable neural network that consists of an encoder and a decoder. The encoder\nis exploited to capture the context of the derived input images, while the\ndecoder is employed to estimate the contribution of each input to the final\ndehazed result using the learned representations attributed to the encoder. The\nconstructed network adopts a novel fusion-based strategy which derives three\ninputs from an original hazy image by applying White Balance (WB), Contrast\nEnhancing (CE), and Gamma Correction (GC). We compute pixel-wise confidence\nmaps based on the appearance differences between these different inputs to\nblend the information of the derived inputs and preserve the regions with\npleasant visibility. The final dehazed image is yielded by gating the important\nfeatures of the derived inputs. To train the network, we introduce a\nmulti-scale approach such that the halo artifacts can be avoided. Extensive\nexperimental results on both synthetic and real-world images demonstrate that\nthe proposed algorithm performs favorably against the state-of-the-art\nalgorithms.","url_abs":"http://arxiv.org/abs/1804.00213v1","url_pdf":"http://arxiv.org/pdf/1804.00213v1.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":[],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-dehazing-on-sots-indoor","task":"Image Dehazing","dataset":"SOTS Indoor","model":"GFN","rank_in_archive_order":30,"of":34,"metrics":{"PSNR":"22.30","SSIM":"0.880"},"uses_additional_data":false},{"leaderboard":"/sota/image-dehazing-on-sots-outdoor","task":"Image Dehazing","dataset":"SOTS Outdoor","model":"GFN","rank_in_archive_order":31,"of":31,"metrics":{"PSNR":"22.30","SSIM":"0.880"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1804.00213","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}