{"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/fast-single-image-dehazing-via-multilevel","title":"Fast Single Image Dehazing via Multilevel Wavelet Transform based Optimization","arxiv_id":"1904.08573","date":"2019-04-18","proceeding":null,"authors":["Jiaxi He","Frank Z. Xing","Ran Yang","Cishen Zhang"],"abstract":"The quality of images captured in outdoor environments can be affected by\npoor weather conditions such as fog, dust, and atmospheric scattering of other\nparticles. This problem can bring extra challenges to high-level computer\nvision tasks like image segmentation and object detection. However, previous\nstudies on image dehazing suffer from a huge computational workload and\ncorruption of the original image, such as over-saturation and halos. In this\npaper, we present a novel image dehazing approach based on the optical model\nfor haze images and regularized optimization. Specifically, we convert the\nnon-convex, bilinear problem concerning the unknown haze-free image and light\ntransmission distribution to a convex, linear optimization problem by\nestimating the atmosphere light constant. Our method is further accelerated by\nintroducing a multilevel Haar wavelet transform. The optimization, instead, is\napplied to the low frequency sub-band decomposition of the original image. This\ndimension reduction significantly improves the processing speed of our method\nand exhibits the potential for real-time applications. Experimental results\nshow that our approach outperforms state-of-the-art dehazing algorithms in\nterms of both image reconstruction quality and computational efficiency. For\nimplementation details, source code can be publicly accessed via\nhttp://github.com/JiaxiHe/Image-and-Video-Dehazing.","url_abs":"http://arxiv.org/abs/1904.08573v1","url_pdf":"http://arxiv.org/pdf/1904.08573v1.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":"fast-single-image-dehazing-via-multilevel","repo_url":"https://github.com/JiaxiHe/Image-and-Video-Dehazing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"single-image-dehazing","task_name":"Single Image Dehazing"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}