{"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/nesti-net-normal-estimation-for-unstructured","title":"Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks","arxiv_id":"1812.00709","date":"2018-12-03","proceeding":"CVPR 2019 6","authors":["Yizhak Ben-Shabat","Michael Lindenbaum","Anath Fischer"],"abstract":"In this paper, we propose a normal estimation method for unstructured 3D\npoint clouds. This method, called Nesti-Net, builds on a new local point cloud\nrepresentation which consists of multi-scale point statistics (MuPS), estimated\non a local coarse Gaussian grid. This representation is a suitable input to a\nCNN architecture. The normals are estimated using a mixture-of-experts (MoE)\narchitecture, which relies on a data-driven approach for selecting the optimal\nscale around each point and encourages sub-network specialization. Interesting\ninsights into the network's resource distribution are provided. The scale\nprediction significantly improves robustness to different noise levels, point\ndensity variations and different levels of detail. We achieve state-of-the-art\nresults on a benchmark synthetic dataset and present qualitative results on\nreal scanned scenes.","url_abs":"http://arxiv.org/abs/1812.00709v1","url_pdf":"http://arxiv.org/pdf/1812.00709v1.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":"nesti-net-normal-estimation-for-unstructured","repo_url":"https://github.com/sitzikbs/Nesti-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"surface-normals-estimation","task_name":"Surface Normals Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/surface-normals-estimation-on-pcpnet","task":"Surface Normals Estimation","dataset":"PCPNet","model":"Nesti-Net","rank_in_archive_order":8,"of":8,"metrics":{"RMSE ":"12.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.00709","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}