{"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/mara-net-single-image-deraining-network-with","title":"MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks","arxiv_id":"2009.13990","date":"2020-09-29","proceeding":null,"authors":["Yeachan Park","Myeongho Jeon","Junho Lee","Myungjoo Kang"],"abstract":"A recent line of convolutional neural network-based works has succeeded in capturing rain streaks. However, difficulties in detailed recovery still remain. In this paper, we present a multi-level connection and wide regional non-local block network (MCW-Net) to properly restore the original background textures in rainy images. Unlike existing encoder-decoder-based image deraining models that improve performance with additional branches, MCW-Net improves performance by maximizing information utilization without additional branches through the following two proposed methods. The first method is a multi-level connection that repeatedly connects multi-level features of the encoder network to the decoder network. Multi-level connection encourages the decoding process to use the feature information of all levels. In multi-level connection, channel-wise attention is considered to learn which level of features is important in the decoding process of the current level. The second method is a wide regional non-local block. As rain streaks primarily exhibit a vertical distribution, we divide the grid of the image into horizontally-wide patches and apply a non-local operation to each region to explore the rich rain-free background information. Experimental results on both synthetic and real-world rainy datasets demonstrate that the proposed model significantly outperforms existing state-of-the-art models. Furthermore, the results of the joint deraining and segmentation experiment prove that our model contributes effectively to other vision tasks.","url_abs":"https://arxiv.org/abs/2009.13990v4","url_pdf":"https://arxiv.org/pdf/2009.13990v4.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":"mara-net-single-image-deraining-network-with","repo_url":"https://github.com/yechanp/MCW-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"rain-removal","task_name":"Rain Removal"},{"task_slug":"single-image-deraining","task_name":"Single Image Deraining"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/single-image-deraining-on-rain100h","task":"Single Image Deraining","dataset":"Rain100H","model":"MCW-Net","rank_in_archive_order":7,"of":19,"metrics":{"PSNR":"30.70","SSIM":"0.922"},"uses_additional_data":false},{"leaderboard":"/sota/single-image-deraining-on-rain100l","task":"Single Image Deraining","dataset":"Rain100L","model":"MCW-Net","rank_in_archive_order":3,"of":19,"metrics":{"PSNR":"39.73","SSIM":"0.988"},"uses_additional_data":false},{"leaderboard":"/sota/single-image-deraining-on-raincityscapes","task":"Single Image Deraining","dataset":"RainCityscapes","model":"MCW-Net","rank_in_archive_order":1,"of":6,"metrics":{"PSNR":"35.82","SSIM":"0.987"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}