{"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/depth-image-inpainting-improving-low-rank","title":"Depth Image Inpainting: Improving Low Rank Matrix Completion with Low Gradient Regularization","arxiv_id":"1604.05817","date":"2016-04-20","proceeding":null,"authors":["Hongyang Xue","Shengming Zhang","Deng Cai"],"abstract":"We consider the case of inpainting single depth images. Without corresponding\ncolor images, previous or next frames, depth image inpainting is quite\nchallenging. One natural solution is to regard the image as a matrix and adopt\nthe low rank regularization just as inpainting color images. However, the low\nrank assumption does not make full use of the properties of depth images.\n  A shallow observation may inspire us to penalize the non-zero gradients by\nsparse gradient regularization. However, statistics show that though most\npixels have zero gradients, there is still a non-ignorable part of pixels whose\ngradients are equal to 1. Based on this specific property of depth images , we\npropose a low gradient regularization method in which we reduce the penalty for\ngradient 1 while penalizing the non-zero gradients to allow for gradual depth\nchanges. The proposed low gradient regularization is integrated with the low\nrank regularization into the low rank low gradient approach for depth image\ninpainting. We compare our proposed low gradient regularization with sparse\ngradient regularization. The experimental results show the effectiveness of our\nproposed approach.","url_abs":"http://arxiv.org/abs/1604.05817v1","url_pdf":"http://arxiv.org/pdf/1604.05817v1.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":"depth-image-inpainting-improving-low-rank","repo_url":"https://github.com/xuehy/depthInpainting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"low-rank-matrix-completion","task_name":"Low-Rank Matrix Completion"},{"task_slug":"matrix-completion","task_name":"Matrix Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.05817","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}