{"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/cylinder3d-an-effective-3d-framework-for","title":"Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation","arxiv_id":"2008.01550","date":"2020-08-04","proceeding":null,"authors":["Hui Zhou","Xinge Zhu","Xiao Song","Yuexin Ma","Zhe Wang","Hongsheng Li","Dahua Lin"],"abstract":"State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. The projection methods includes spherical projection, bird-eye view projection, etc. Although this process makes the point cloud suitable for the 2D CNN-based networks, it inevitably alters and abandons the 3D topology and geometric relations. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. In this work, we first perform an in-depth analysis for different representations and backbones in 2D and 3D spaces, and reveal the effectiveness of 3D representations and networks on LiDAR segmentation. Then, we develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds. Moreover, a dimension-decomposition based context modeling module is introduced to explore the high-rank context information in point clouds in a progressive manner. We evaluate the proposed model on a large-scale driving-scene dataset, i.e. SematicKITTI. Our method achieves state-of-the-art performance and outperforms existing methods by 6% in terms of mIoU.","url_abs":"https://arxiv.org/abs/2008.01550v1","url_pdf":"https://arxiv.org/pdf/2008.01550v1.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":"cylinder3d-an-effective-3d-framework-for","repo_url":"https://github.com/xinge008/Cylinder3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cylinder3d-an-effective-3d-framework-for","repo_url":"https://github.com/L-Reichardt/Cylinder3D-updated-CUDA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"cylinder3d-an-effective-3d-framework-for","repo_url":"https://github.com/hongfz16/DS-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-nuscenes","task":"3D Object Detection","dataset":"nuScenes","model":"Reconfig PP v3","rank_in_archive_order":192,"of":372,"metrics":{"NDS":"0.59","mAAE":"0.24","mAOE":"0.44","mAP":"0.49","mASE":"0.24","mATE":"0.33","mAVE":"0.27"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-wildscenes","task":"3D Semantic Segmentation","dataset":"WildScenes","model":"Cylinder3D","rank_in_archive_order":1,"of":4,"metrics":{"mIoU":"40.07"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"Cylinder3D++","rank_in_archive_order":14,"of":36,"metrics":{"test mIoU":"0.78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.01550","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}