{"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/dynamic-local-geometry-capture-in-3d","title":"Dynamic Local Geometry Capture in 3D PointCloud Classification","arxiv_id":null,"date":"2021-10-19","proceeding":"IEEE 4th International Conference on Multimedia Information Processing and Retrieval (MIPR) 2021 10","authors":["Shivanand Venkanna Sheshappanavar","Chandra Kambhamettu"],"abstract":"With the advent of PointNet, the popularity of deep neural networks has increased in point cloud analysis. PointNet's successor, PointNet++, partitions the input point cloud and recursively applies PointNet to capture local geometry. PointNet++ model uses ball querying for local geometry capture in its set abstraction layers. Several models based on single-scale grouping of PointNet++ continue to use ball querying with a fixed-radius ball. Due to its uniform scale in all directions, a ball lacks orientation and is ineffective in capturing complex local neighborhoods. Few recent models replace a fixed-sized ball with a fixed-sized ellipsoid or a fixed-sized cuboid to capture local neighborhoods. However, these methods are not still fully effective in capturing varying geometry proportions from different local neighborhoods on the object surface. We propose a novel technique of dynamically oriented and scaled ellipsoid based on unique local information to capture the local geometry better. We also propose ReducedPointNet++, a single set abstraction-based single scale grouping model. Our model, along with dynamically oriented and scaled ellipsoid querying, achieves 92.1% classification accuracy on the ModelNet40 dataset. We achieve state-of-the-art 3D classification results on all six variants of the real-world ScanObjectNN dataset with an accuracy of 82.0% on the most challenging variant.","url_abs":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9565556","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9565556","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":"dynamic-local-geometry-capture-in-3d","repo_url":"https://github.com/VimsLab/DynamicScale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-classification","task_name":"3D Classification"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"classification-1","task_name":"Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"DynamicScale","rank_in_archive_order":94,"of":111,"metrics":{"Overall Accuracy":"92.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"DynamicScale","rank_in_archive_order":67,"of":77,"metrics":{"Overall Accuracy":"82.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}