{"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/learning-to-sample","title":"Learning to Sample","arxiv_id":"1812.01659","date":"2018-12-04","proceeding":"CVPR 2019 6","authors":["Oren Dovrat","Itai Lang","Shai Avidan"],"abstract":"Processing large point clouds is a challenging task. Therefore, the data is\noften sampled to a size that can be processed more easily. The question is how\nto sample the data? A popular sampling technique is Farthest Point Sampling\n(FPS). However, FPS is agnostic to a downstream application (classification,\nretrieval, etc.). The underlying assumption seems to be that minimizing the\nfarthest point distance, as done by FPS, is a good proxy to other objective\nfunctions.\n  We show that it is better to learn how to sample. To do that, we propose a\ndeep network to simplify 3D point clouds. The network, termed S-NET, takes a\npoint cloud and produces a smaller point cloud that is optimized for a\nparticular task. The simplified point cloud is not guaranteed to be a subset of\nthe original point cloud. Therefore, we match it to a subset of the original\npoints in a post-processing step. We contrast our approach with FPS by\nexperimenting on two standard data sets and show significantly better results\nfor a variety of applications. Our code is publicly available at:\nhttps://github.com/orendv/learning_to_sample","url_abs":"http://arxiv.org/abs/1812.01659v2","url_pdf":"http://arxiv.org/pdf/1812.01659v2.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":"learning-to-sample","repo_url":"https://github.com/orendv/learning_to_sample","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-point-cloud-reconstruction","task_name":"3D Point Cloud Reconstruction"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}