{"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/mamba24-8d-enhancing-global-interaction-in","title":"Pamba: Enhancing Global Interaction in Point Clouds via State Space Model","arxiv_id":"2406.17442","date":"2024-06-25","proceeding":null,"authors":["Zhuoyuan Li","Yubo Ai","Jiahao Lu","Chuxin Wang","Jiacheng Deng","Hanzhi Chang","Yanzhe Liang","Wenfei Yang","Shifeng Zhang","Tianzhu Zhang"],"abstract":"Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously and impeding the modeling of long-range dependencies between objects in a single scene. Drawing inspiration from the great potential of recent state space models (SSM) for long sequence modeling, we introduce Mamba, an SSM-based architecture, to the point cloud domain and propose Pamba, a novel architecture with strong global modeling capability under linear complexity. Specifically, to make the disorderness of point clouds fit in with the causal nature of Mamba, we propose a multi-path serialization strategy applicable to point clouds. Besides, we propose the ConvMamba block to compensate for the shortcomings of Mamba in modeling local geometries and in unidirectional modeling. Pamba obtains state-of-the-art results on several 3D point cloud segmentation tasks, including ScanNet v2, ScanNet200, S3DIS and nuScenes, while its effectiveness is validated by extensive experiments.","url_abs":"https://arxiv.org/abs/2406.17442v3","url_pdf":"https://arxiv.org/pdf/2406.17442v3.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-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet200","task":"3D Semantic Segmentation","dataset":"ScanNet200","model":"Pamba","rank_in_archive_order":6,"of":16,"metrics":{"test mIoU":"37.1","val mIoU":"36.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"Pamba","rank_in_archive_order":12,"of":61,"metrics":{"mIoU":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannet","task":"Semantic Segmentation","dataset":"ScanNet","model":"Pamba","rank_in_archive_order":7,"of":45,"metrics":{"val mIoU":"77.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.17442","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}