{"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/progressive-feature-fusion-network-for","title":"Progressive Feature Fusion Network for Realistic Image Dehazing","arxiv_id":"1810.02283","date":"2018-10-04","proceeding":null,"authors":["Kangfu Mei","Aiwen Jiang","Juncheng Li","Mingwen Wang"],"abstract":"Single image dehazing is a challenging ill-posed restoration problem. Various\nprior-based and learning-based methods have been proposed. Most of them follow\na classic atmospheric scattering model which is an elegant simplified physical\nmodel based on the assumption of single-scattering and homogeneous atmospheric\nmedium. The formulation of haze in realistic environment is more complicated.\nIn this paper, we propose to take its essential mechanism as \"black box\", and\nfocus on learning an input-adaptive trainable end-to-end dehazing model. An\nU-Net like encoder-decoder deep network via progressive feature fusions has\nbeen proposed to directly learn highly nonlinear transformation function from\nobserved hazy image to haze-free ground-truth. The proposed network is\nevaluated on two public image dehazing benchmarks. The experiments demonstrate\nthat it can achieve superior performance when compared with popular\nstate-of-the-art methods. With efficient GPU memory usage, it can\nsatisfactorily recover ultra high definition hazed image up to 4K resolution,\nwhich is unaffordable by many deep learning based dehazing algorithms.","url_abs":"http://arxiv.org/abs/1810.02283v1","url_pdf":"http://arxiv.org/pdf/1810.02283v1.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":"progressive-feature-fusion-network-for","repo_url":"https://github.com/MKFMIKU/PFFNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.02283","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}