{"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/a-trilateral-weighted-sparse-coding-scheme","title":"A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising","arxiv_id":"1807.04364","date":"2018-07-11","proceeding":"ECCV 2018 9","authors":["Jun Xu","Lei Zhang","David Zhang"],"abstract":"Most of existing image denoising methods assume the corrupted noise to be\nadditive white Gaussian noise (AWGN). However, the realistic noise in\nreal-world noisy images is much more complex than AWGN, and is hard to be\nmodelled by simple analytical distributions. As a result, many state-of-the-art\ndenoising methods in literature become much less effective when applied to\nreal-world noisy images captured by CCD or CMOS cameras. In this paper, we\ndevelop a trilateral weighted sparse coding (TWSC) scheme for robust real-world\nimage denoising. Specifically, we introduce three weight matrices into the data\nand regularisation terms of the sparse coding framework to characterise the\nstatistics of realistic noise and image priors. TWSC can be reformulated as a\nlinear equality-constrained problem and can be solved by the alternating\ndirection method of multipliers. The existence and uniqueness of the solution\nand convergence of the proposed algorithm are analysed. Extensive experiments\ndemonstrate that the proposed TWSC scheme outperforms state-of-the-art\ndenoising methods on removing realistic noise.","url_abs":"http://arxiv.org/abs/1807.04364v1","url_pdf":"http://arxiv.org/pdf/1807.04364v1.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":[],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/color-image-denoising-on-darmstadt-noise","task":"Color Image Denoising","dataset":"Darmstadt Noise Dataset","model":"TWSC","rank_in_archive_order":5,"of":6,"metrics":{"PSNR (sRGB)":"37.94","SSIM (sRGB)":"0.9403"},"uses_additional_data":false},{"leaderboard":"/sota/denoising-on-darmstadt-noise-dataset","task":"Denoising","dataset":"Darmstadt Noise Dataset","model":"TWSC","rank_in_archive_order":3,"of":10,"metrics":{"PSNR":"37.93"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.04364","atlas_url":"https://app.syntology.ai/?focus=1807.04364","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}