{"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/tearingnet-point-cloud-autoencoder-to-learn","title":"TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations","arxiv_id":"2006.10187","date":"2020-06-17","proceeding":"CVPR 2021 1","authors":["Jiahao Pang","Duanshun Li","Dong Tian"],"abstract":"Topology matters. Despite the recent success of point cloud processing with geometric deep learning, it remains arduous to capture the complex topologies of point cloud data with a learning model. Given a point cloud dataset containing objects with various genera, or scenes with multiple objects, we propose an autoencoder, TearingNet, which tackles the challenging task of representing the point clouds using a fixed-length descriptor. Unlike existing works directly deforming predefined primitives of genus zero (e.g., a 2D square patch) to an object-level point cloud, our TearingNet is characterized by a proposed Tearing network module and a Folding network module interacting with each other iteratively. Particularly, the Tearing network module learns the point cloud topology explicitly. By breaking the edges of a primitive graph, it tears the graph into patches or with holes to emulate the topology of a target point cloud, leading to faithful reconstructions. Experimentation shows the superiority of our proposal in terms of reconstructing point clouds as well as generating more topology-friendly representations than benchmarks.","url_abs":"https://arxiv.org/abs/2006.10187v4","url_pdf":"https://arxiv.org/pdf/2006.10187v4.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":"tearingnet-point-cloud-autoencoder-to-learn","repo_url":"https://github.com/InterDigitalInc/TearingNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.10187","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}