{"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/learning-pixel-distribution-prior-with-wider","title":"Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising","arxiv_id":"1707.09135","date":"2017-07-28","proceeding":null,"authors":["Peng Liu","Ruogu Fang"],"abstract":"In this work, we explore an innovative strategy for image denoising by using\nconvolutional neural networks (CNN) to learn pixel-distribution from noisy\ndata. By increasing CNN's width with large reception fields and more channels\nin each layer, CNNs can reveal the ability to learn pixel-distribution, which\nis a prior existing in many different types of noise. The key to our approach\nis a discovery that wider CNNs tends to learn the pixel-distribution features,\nwhich provides the probability of that inference-mapping primarily relies on\nthe priors instead of deeper CNNs with more stacked nonlinear layers. We\nevaluate our work: Wide inference Networks (WIN) on additive white Gaussian\nnoise (AWGN) and demonstrate that by learning the pixel-distribution in images,\nWIN-based network consistently achieves significantly better performance than\ncurrent state-of-the-art deep CNN-based methods in both quantitative and visual\nevaluations. \\textit{Code and models are available at\n\\url{https://github.com/cswin/WIN}}.","url_abs":"http://arxiv.org/abs/1707.09135v1","url_pdf":"http://arxiv.org/pdf/1707.09135v1.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":"learning-pixel-distribution-prior-with-wider","repo_url":"https://github.com/cswin/WIN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}