{"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-a-dilated-residual-network-for-sar","title":"Learning a Dilated Residual Network for SAR Image Despeckling","arxiv_id":"1709.02898","date":"2017-09-09","proceeding":null,"authors":["Qiang Zhang","Qiangqiang Yuan","Jie Li","Zhen Yang","Xiaoshuang Ma"],"abstract":"In this paper, to break the limit of the traditional linear models for\nsynthetic aperture radar (SAR) image despeckling, we propose a novel deep\nlearning approach by learning a non-linear end-to-end mapping between the noisy\nand clean SAR images with a dilated residual network (SAR-DRN). SAR-DRN is\nbased on dilated convolutions, which can both enlarge the receptive field and\nmaintain the filter size and layer depth with a lightweight structure. In\naddition, skip connections and residual learning strategy are added to the\ndespeckling model to maintain the image details and reduce the vanishing\ngradient problem. Compared with the traditional despeckling methods, the\nproposed method shows superior performance over the state-of-the-art methods on\nboth quantitative and visual assessments, especially for strong speckle noise.","url_abs":"http://arxiv.org/abs/1709.02898v3","url_pdf":"http://arxiv.org/pdf/1709.02898v3.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-a-dilated-residual-network-for-sar","repo_url":"https://github.com/qzhang95/SAR-DRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sar-image-despeckling","task_name":"Sar Image Despeckling"}],"methods":[],"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}