{"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/an-all-in-one-network-for-dehazing-and-beyond","title":"An All-in-One Network for Dehazing and Beyond","arxiv_id":"1707.06543","date":"2017-07-20","proceeding":null,"authors":["Boyi Li","Xiulian Peng","Zhangyang Wang","Jizheng Xu","Dan Feng"],"abstract":"This paper proposes an image dehazing model built with a convolutional neural\nnetwork (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed\nbased on a re-formulated atmospheric scattering model. Instead of estimating\nthe transmission matrix and the atmospheric light separately as most previous\nmodels did, AOD-Net directly generates the clean image through a light-weight\nCNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other\ndeep models, e.g., Faster R-CNN, for improving high-level task performance on\nhazy images. Experimental results on both synthesized and natural hazy image\ndatasets demonstrate our superior performance than the state-of-the-art in\nterms of PSNR, SSIM and the subjective visual quality. Furthermore, when\nconcatenating AOD-Net with Faster R-CNN and training the joint pipeline from\nend to end, we witness a large improvement of the object detection performance\non hazy images.","url_abs":"http://arxiv.org/abs/1707.06543v1","url_pdf":"http://arxiv.org/pdf/1707.06543v1.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":"an-all-in-one-network-for-dehazing-and-beyond","repo_url":"https://github.com/elras/desmokenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"an-all-in-one-network-for-dehazing-and-beyond","repo_url":"https://github.com/soumik12345/AODNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"image-dehazing","task_name":"Image Dehazing"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.06543","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}