{"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/multi-chart-generative-surface-modeling","title":"Multi-chart Generative Surface Modeling","arxiv_id":"1806.02143","date":"2018-06-06","proceeding":null,"authors":["Heli Ben-Hamu","Haggai Maron","Itay Kezurer","Gal Avineri","Yaron Lipman"],"abstract":"This paper introduces a 3D shape generative model based on deep neural\nnetworks. A new image-like (i.e., tensor) data representation for genus-zero 3D\nshapes is devised. It is based on the observation that complicated shapes can\nbe well represented by multiple parameterizations (charts), each focusing on a\ndifferent part of the shape. The new tensor data representation is used as\ninput to Generative Adversarial Networks for the task of 3D shape generation.\nThe 3D shape tensor representation is based on a multi-chart structure that\nenjoys a shape covering property and scale-translation rigidity.\nScale-translation rigidity facilitates high quality 3D shape learning and\nguarantees unique reconstruction. The multi-chart structure uses as input a\ndataset of 3D shapes (with arbitrary connectivity) and a sparse correspondence\nbetween them. The output of our algorithm is a generative model that learns the\nshape distribution and is able to generate novel shapes, interpolate shapes,\nand explore the generated shape space. The effectiveness of the method is\ndemonstrated for the task of anatomic shape generation including human body and\nbone (teeth) shape generation.","url_abs":"http://arxiv.org/abs/1806.02143v3","url_pdf":"http://arxiv.org/pdf/1806.02143v3.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":"multi-chart-generative-surface-modeling","repo_url":"https://github.com/helibenhamu/multichart3dgans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02143","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}