{"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/geometrics-exploiting-geometric-structure-for","title":"GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects","arxiv_id":"1901.11461","date":"2019-01-31","proceeding":null,"authors":["Edward J. Smith","Scott Fujimoto","Adriana Romero","David Meger"],"abstract":"Mesh models are a promising approach for encoding the structure of 3D\nobjects. Current mesh reconstruction systems predict uniformly distributed\nvertex locations of a predetermined graph through a series of graph\nconvolutions, leading to compromises with respect to performance or resolution.\nIn this paper, we argue that the graph representation of geometric objects\nallows for additional structure, which should be leveraged for enhanced\nreconstruction. Thus, we propose a system which properly benefits from the\nadvantages of the geometric structure of graph encoded objects by introducing\n(1) a graph convolutional update preserving vertex information; (2) an adaptive\nsplitting heuristic allowing detail to emerge; and (3) a training objective\noperating both on the local surfaces defined by vertices as well as the global\nstructure defined by the mesh. Our proposed method is evaluated on the task of\n3D object reconstruction from images with the ShapeNet dataset, where we\ndemonstrate state of the art performance, both visually and numerically, while\nhaving far smaller space requirements by generating adaptive meshes","url_abs":"http://arxiv.org/abs/1901.11461v1","url_pdf":"http://arxiv.org/pdf/1901.11461v1.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":"geometrics-exploiting-geometric-structure-for","repo_url":"https://github.com/EdwardSmith1884/GEOMetrics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-reconstruction","task_name":"3D Object Reconstruction"},{"task_slug":"object-reconstruction","task_name":"Object Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-reconstruction-on-data3dr2n2","task":"3D Object Reconstruction","dataset":"Data3D−R2N2","model":"GEOMetrics","rank_in_archive_order":10,"of":15,"metrics":{"Avg F1":"67.37"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.11461","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}