{"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/scan2mesh-from-unstructured-range-scans-to-3d","title":"Scan2Mesh: From Unstructured Range Scans to 3D Meshes","arxiv_id":"1811.10464","date":"2018-11-26","proceeding":"CVPR 2019 6","authors":["Angela Dai","Matthias Nießner"],"abstract":"We introduce Scan2Mesh, a novel data-driven generative approach which\ntransforms an unstructured and potentially incomplete range scan into a\nstructured 3D mesh representation. The main contribution of this work is a\ngenerative neural network architecture whose input is a range scan of a 3D\nobject and whose output is an indexed face set conditioned on the input scan.\nIn order to generate a 3D mesh as a set of vertices and face indices, the\ngenerative model builds on a series of proxy losses for vertices, edges, and\nfaces. At each stage, we realize a one-to-one discrete mapping between the\npredicted and ground truth data points with a combination of convolutional- and\ngraph neural network architectures. This enables our algorithm to predict a\ncompact mesh representation similar to those created through manual artist\neffort using 3D modeling software. Our generated mesh results thus produce\nsharper, cleaner meshes with a fundamentally different structure from those\ngenerated through implicit functions, a first step in bridging the gap towards\nartist-created CAD models.","url_abs":"http://arxiv.org/abs/1811.10464v2","url_pdf":"http://arxiv.org/pdf/1811.10464v2.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":"scan2mesh-from-unstructured-range-scans-to-3d","repo_url":"https://github.com/MohamedRamzy1/Scan2Mesh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10464","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}