{"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/deep-graph-convolutional-image-denoising","title":"Deep Graph-Convolutional Image Denoising","arxiv_id":"1907.08448","date":"2019-07-19","proceeding":null,"authors":["Diego Valsesia","Giulia Fracastoro","Enrico Magli"],"abstract":"Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite only exploiting local information. In this paper, we propose a novel end-to-end trainable neural network architecture employing layers based on graph convolution operations, thereby creating neurons with non-local receptive fields. The graph convolution operation generalizes the classic convolution to arbitrary graphs. In this work, the graph is dynamically computed from similarities among the hidden features of the network, so that the powerful representation learning capabilities of the network are exploited to uncover self-similar patterns. We introduce a lightweight Edge-Conditioned Convolution which addresses vanishing gradient and over-parameterization issues of this particular graph convolution. Extensive experiments show state-of-the-art performance with improved qualitative and quantitative results on both synthetic Gaussian noise and real noise.","url_abs":"https://arxiv.org/abs/1907.08448v1","url_pdf":"https://arxiv.org/pdf/1907.08448v1.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":"deep-graph-convolutional-image-denoising","repo_url":"https://github.com/diegovalsesia/gcdn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma15","task":"Grayscale Image Denoising","dataset":"BSD68 sigma15","model":"GCDN","rank_in_archive_order":7,"of":16,"metrics":{"PSNR":"31.83"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma25","task":"Grayscale Image Denoising","dataset":"BSD68 sigma25","model":"GCDN","rank_in_archive_order":6,"of":16,"metrics":{"PSNR":"29.35"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma50","task":"Grayscale Image Denoising","dataset":"BSD68 sigma50","model":"GCDN","rank_in_archive_order":10,"of":15,"metrics":{"PSNR":"26.38"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma15","task":"Grayscale Image Denoising","dataset":"Set12 sigma15","model":"GCDN","rank_in_archive_order":5,"of":8,"metrics":{"PSNR":"33.14"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma25","task":"Grayscale Image Denoising","dataset":"Set12 sigma25","model":"GCDN","rank_in_archive_order":4,"of":6,"metrics":{"PSNR":"30.78"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-set12-sigma50","task":"Grayscale Image Denoising","dataset":"Set12 sigma50","model":"GCDN","rank_in_archive_order":5,"of":8,"metrics":{"PSNR":"27.6"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma15","task":"Grayscale Image Denoising","dataset":"Urban100 sigma15","model":"GCDN","rank_in_archive_order":3,"of":7,"metrics":{"PSNR":"33.47"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma25","task":"Grayscale Image Denoising","dataset":"Urban100 sigma25","model":"GCDN","rank_in_archive_order":6,"of":10,"metrics":{"PSNR":"30.95"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-urban100-sigma50","task":"Grayscale Image Denoising","dataset":"Urban100 sigma50","model":"GCDN","rank_in_archive_order":9,"of":10,"metrics":{"PSNR":"27.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.08448","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}