{"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/vidosat-high-dimensional-sparsifying","title":"VIDOSAT: High-dimensional Sparsifying Transform Learning for Online Video Denoising","arxiv_id":"1710.00947","date":"2017-10-03","proceeding":null,"authors":["Bihan Wen","Saiprasad Ravishankar","Yoram Bresler"],"abstract":"Techniques exploiting the sparsity of images in a transform domain have been\neffective for various applications in image and video processing. Transform\nlearning methods involve cheap computations and have been demonstrated to\nperform well in applications such as image denoising and medical image\nreconstruction. Recently, we proposed methods for online learning of\nsparsifying transforms from streaming signals, which enjoy good convergence\nguarantees, and involve lower computational costs than online synthesis\ndictionary learning. In this work, we apply online transform learning to video\ndenoising. We present a novel framework for online video denoising based on\nhigh-dimensional sparsifying transform learning for spatio-temporal patches.\nThe patches are constructed either from corresponding 2D patches in successive\nframes or using an online block matching technique. The proposed online video\ndenoising requires little memory, and offers efficient processing. Numerical\nexperiments compare the performance to the proposed video denoising scheme but\nfixing the transform to be 3D DCT, as well as prior schemes such as dictionary\nlearning-based schemes, and the state-of-the-art VBM3D and VBM4D on several\nvideo data sets, demonstrating the promising performance of the proposed\nmethods.","url_abs":"http://arxiv.org/abs/1710.00947v1","url_pdf":"http://arxiv.org/pdf/1710.00947v1.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":"vidosat-high-dimensional-sparsifying","repo_url":"https://github.com/wenbihan/vidosat_icip2015","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"dictionary-learning","task_name":"Dictionary Learning"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"video-denoising","task_name":"Video Denoising"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}