{"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/grdngrouped-residual-dense-network-for-real","title":"GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling","arxiv_id":"1905.11172","date":"2019-05-27","proceeding":null,"authors":["Dong-Wook Kim","Jae Ryun Chung","Seung-Won Jung"],"abstract":"Recent research on image denoising has progressed with the development of deep learning architectures, especially convolutional neural networks. However, real-world image denoising is still very challenging because it is not possible to obtain ideal pairs of ground-truth images and real-world noisy images. Owing to the recent release of benchmark datasets, the interest of the image denoising community is now moving toward the real-world denoising problem. In this paper, we propose a grouped residual dense network (GRDN), which is an extended and generalized architecture of the state-of-the-art residual dense network (RDN). The core part of RDN is defined as grouped residual dense block (GRDB) and used as a building module of GRDN. We experimentally show that the image denoising performance can be significantly improved by cascading GRDBs. In addition to the network architecture design, we also develop a new generative adversarial network-based real-world noise modeling method. We demonstrate the superiority of the proposed methods by achieving the highest score in terms of both the peak signal-to-noise ratio and the structural similarity in the NTIRE2019 Real Image Denoising Challenge - Track 2:sRGB.","url_abs":"https://arxiv.org/abs/1905.11172v1","url_pdf":"https://arxiv.org/pdf/1905.11172v1.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":"grdngrouped-residual-dense-network-for-real","repo_url":"https://github.com/caiyuanhao1998/PNGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"grdngrouped-residual-dense-network-for-real","repo_url":"https://github.com/merria28/NTIRE_GRDN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"noise-estimation","task_name":"Noise Estimation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/color-image-denoising-on-ntire-2019-real","task":"Color Image Denoising","dataset":"NTIRE 2019 Real Image Denoising Challenge (sRGB)","model":"GRDN","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"39.931743","SSIM":"0.973589"},"uses_additional_data":false},{"leaderboard":"/sota/noise-estimation-on-sidd","task":"Noise Estimation","dataset":"SIDD","model":"GRDN","rank_in_archive_order":3,"of":5,"metrics":{"Average KL Divergence":"0.443","PSNR Gap":"2.28"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.11172","atlas_url":"https://app.syntology.ai/?focus=1905.11172","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}