{"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/class-aware-fully-convolutional-gaussian-and","title":"Class-Aware Fully-Convolutional Gaussian and Poisson Denoising","arxiv_id":"1808.06562","date":"2018-08-20","proceeding":null,"authors":["Tal Remez","Or Litany","Raja Giryes","Alex M. Bronstein"],"abstract":"We propose a fully-convolutional neural-network architecture for image\ndenoising which is simple yet powerful. Its structure allows to exploit the\ngradual nature of the denoising process, in which shallow layers handle local\nnoise statistics, while deeper layers recover edges and enhance textures. Our\nmethod advances the state-of-the-art when trained for different noise levels\nand distributions (both Gaussian and Poisson). In addition, we show that making\nthe denoiser class-aware by exploiting semantic class information boosts\nperformance, enhances textures and reduces artifacts.","url_abs":"http://arxiv.org/abs/1808.06562v1","url_pdf":"http://arxiv.org/pdf/1808.06562v1.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":"class-aware-fully-convolutional-gaussian-and","repo_url":"https://github.com/TalRemez/deep_class_aware_denoising","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","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":"https://app.syntology.ai/?focus=1808.06562","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}