{"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/fast-and-accurate-tensor-completion-with","title":"Fast and Accurate Tensor Completion with Total Variation Regularized Tensor Trains","arxiv_id":"1804.06128","date":"2018-04-17","proceeding":null,"authors":["Ching-Yun Ko","Kim Batselier","Wenjian Yu","Ngai Wong"],"abstract":"We propose a new tensor completion method based on tensor trains. The\nto-be-completed tensor is modeled as a low-rank tensor train, where we use the\nknown tensor entries and their coordinates to update the tensor train. A novel\ntensor train initialization procedure is proposed specifically for image and\nvideo completion, which is demonstrated to ensure fast convergence of the\ncompletion algorithm. The tensor train framework is also shown to easily\naccommodate Total Variation and Tikhonov regularization due to their low-rank\ntensor train representations. Image and video inpainting experiments verify the\nsuperiority of the proposed scheme in terms of both speed and scalability,\nwhere a speedup of up to 155X is observed compared to state-of-the-art tensor\ncompletion methods at a similar accuracy. Moreover, we demonstrate the proposed\nscheme is especially advantageous over existing algorithms when only tiny\nportions (say, 1%) of the to-be-completed images/videos are known.","url_abs":"http://arxiv.org/abs/1804.06128v3","url_pdf":"http://arxiv.org/pdf/1804.06128v3.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":"fast-and-accurate-tensor-completion-with","repo_url":"https://github.com/IRENEKO/TTC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"video-inpainting","task_name":"Video Inpainting"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}