{"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/patch-based-progressive-3d-point-set","title":"Patch-based Progressive 3D Point Set Upsampling","arxiv_id":"1811.11286","date":"2018-11-27","proceeding":"CVPR 2019 6","authors":["Wang Yifan","Shihao Wu","Hui Huang","Daniel Cohen-Or","Olga Sorkine-Hornung"],"abstract":"We present a detail-driven deep neural network for point set upsampling. A\nhigh-resolution point set is essential for point-based rendering and surface\nreconstruction. Inspired by the recent success of neural image super-resolution\ntechniques, we progressively train a cascade of patch-based upsampling networks\non different levels of detail end-to-end. We propose a series of architectural\ndesign contributions that lead to a substantial performance boost. The effect\nof each technical contribution is demonstrated in an ablation study.\nQualitative and quantitative experiments show that our method significantly\noutperforms the state-of-the-art learning-based and optimazation-based\napproaches, both in terms of handling low-resolution inputs and revealing\nhigh-fidelity details.","url_abs":"http://arxiv.org/abs/1811.11286v3","url_pdf":"http://arxiv.org/pdf/1811.11286v3.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":"patch-based-progressive-3d-point-set","repo_url":"https://github.com/yifita/3PU_pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"patch-based-progressive-3d-point-set","repo_url":"https://github.com/yifita/3PU","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"patch-based-progressive-3d-point-set","repo_url":"https://github.com/guochengqian/PU-GCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"point-cloud-super-resolution","task_name":"Point Cloud Super Resolution"},{"task_slug":"point-set-upsampling","task_name":"Point Set Upsampling"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.11286","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}