{"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/octree-guided-cnn-with-spherical-kernels-for","title":"Octree guided CNN with Spherical Kernels for 3D Point Clouds","arxiv_id":"1903.00343","date":"2019-02-28","proceeding":"CVPR 2019 6","authors":["Huan Lei","Naveed Akhtar","Ajmal Mian"],"abstract":"We propose an octree guided neural network architecture and spherical\nconvolutional kernel for machine learning from arbitrary 3D point clouds. The\nnetwork architecture capitalizes on the sparse nature of irregular point\nclouds, and hierarchically coarsens the data representation with space\npartitioning. At the same time, the proposed spherical kernels systematically\nquantize point neighborhoods to identify local geometric structures in the\ndata, while maintaining the properties of translation-invariance and asymmetry.\nWe specify spherical kernels with the help of network neurons that in turn are\nassociated with spatial locations. We exploit this association to avert dynamic\nkernel generation during network training that enables efficient learning with\nhigh resolution point clouds. The effectiveness of the proposed technique is\nestablished on the benchmark tasks of 3D object classification and\nsegmentation, achieving new state-of-the-art on ShapeNet and RueMonge2014\ndatasets.","url_abs":"http://arxiv.org/abs/1903.00343v1","url_pdf":"http://arxiv.org/pdf/1903.00343v1.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":[],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"Ps-CNN","rank_in_archive_order":14,"of":67,"metrics":{"Class Average IoU":"83.4","Instance Average IoU":"86.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.00343","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}