{"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/multiresolution-tree-networks-for-3d-point","title":"Multiresolution Tree Networks for 3D Point Cloud Processing","arxiv_id":"1807.03520","date":"2018-07-10","proceeding":"ECCV 2018 9","authors":["Matheus Gadelha","Rui Wang","Subhransu Maji"],"abstract":"We present multiresolution tree-structured networks to process point clouds\nfor 3D shape understanding and generation tasks. Our network represents a 3D\nshape as a set of locality-preserving 1D ordered list of points at multiple\nresolutions. This allows efficient feed-forward processing through 1D\nconvolutions, coarse-to-fine analysis through a multi-grid architecture, and it\nleads to faster convergence and small memory footprint during training. The\nproposed tree-structured encoders can be used to classify shapes and outperform\nexisting point-based architectures on shape classification benchmarks, while\ntree-structured decoders can be used for generating point clouds directly and\nthey outperform existing approaches for image-to-shape inference tasks learned\nusing the ShapeNet dataset. Our model also allows unsupervised learning of\npoint-cloud based shapes by using a variational autoencoder, leading to\nhigher-quality generated shapes.","url_abs":"http://arxiv.org/abs/1807.03520v2","url_pdf":"http://arxiv.org/pdf/1807.03520v2.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":"multiresolution-tree-networks-for-3d-point","repo_url":"https://github.com/matheusgadelha/MRTNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.03520","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}