{"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/spatial-adaptive-network-for-single-image","title":"Spatial-Adaptive Network for Single Image Denoising","arxiv_id":"2001.10291","date":"2020-01-28","proceeding":"ECCV 2020 8","authors":["Meng Chang","Qi Li","Huajun Feng","Zhihai Xu"],"abstract":"Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network structure could alleviate these problems, but more computational overhead is needed. In this paper, we propose a novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal. To adapt to changes in spatial textures and edges, we design a residual spatial-adaptive block. Deformable convolution is introduced to sample the spatially correlated features for weighting. An encoder-decoder structure with a context block is introduced to capture multiscale information. With noise removal from the coarse to fine, a high-quality noisefree image can be obtained. We apply our method to both synthetic and real noisy image datasets. The experimental results demonstrate that our method can surpass the state-of-the-art denoising methods both quantitatively and visually.","url_abs":"https://arxiv.org/abs/2001.10291v2","url_pdf":"https://arxiv.org/pdf/2001.10291v2.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":"spatial-adaptive-network-for-single-image","repo_url":"https://github.com/JimmyChame/SADNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"spatial-adaptive-network-for-single-image","repo_url":"https://github.com/sami-automatic/SADNet_Replication","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deformable-convolution","method_name":"Deformable Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-denoising-on-dnd","task":"Image Denoising","dataset":"DND","model":"SADNet","rank_in_archive_order":10,"of":16,"metrics":{"PSNR (sRGB)":"39.59","SSIM (sRGB)":"0.952"},"uses_additional_data":true},{"leaderboard":"/sota/image-denoising-on-sidd","task":"Image Denoising","dataset":"SIDD","model":"SADNet","rank_in_archive_order":16,"of":22,"metrics":{"PSNR (sRGB)":"39.46","SSIM (sRGB)":"0.957"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.10291","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}