{"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/gfnet-geometric-flow-network-for-3d-point","title":"GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation","arxiv_id":"2207.02605","date":"2022-07-06","proceeding":null,"authors":["Haibo Qiu","Baosheng Yu","DaCheng Tao"],"abstract":"Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are complementary to each other. However, recent projection-based methods for point cloud semantic segmentation usually utilize a vanilla late fusion strategy for the predictions of different views, failing to explore the complementary information from a geometric perspective during the representation learning. In this paper, we introduce a geometric flow network (GFNet) to explore the geometric correspondence between different views in an align-before-fuse manner. Specifically, we devise a novel geometric flow module (GFM) to bidirectionally align and propagate the complementary information across different views according to geometric relationships under the end-to-end learning scheme. We perform extensive experiments on two widely used benchmark datasets, SemanticKITTI and nuScenes, to demonstrate the effectiveness of our GFNet for project-based point cloud semantic segmentation. Concretely, GFNet not only significantly boosts the performance of each individual view but also achieves state-of-the-art results over all existing projection-based models. Code is available at \\url{https://github.com/haibo-qiu/GFNet}.","url_abs":"https://arxiv.org/abs/2207.02605v2","url_pdf":"https://arxiv.org/pdf/2207.02605v2.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":"gfnet-geometric-flow-network-for-3d-point","repo_url":"https://github.com/haibo-qiu/gfnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"robust-3d-semantic-segmentation","task_name":"Robust 3D Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"GFNet","rank_in_archive_order":16,"of":45,"metrics":{"test mIoU":"65.4%"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"GFNet","rank_in_archive_order":21,"of":36,"metrics":{"test mIoU":"0.76"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on","task":"Robust 3D Semantic Segmentation","dataset":"SemanticKITTI-C","model":"GFNet","rank_in_archive_order":13,"of":22,"metrics":{"mean Corruption Error (mCE)":"108.68%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on-nuscenes-c","task":"Robust 3D Semantic Segmentation","dataset":"nuScenes-C","model":"GFNet","rank_in_archive_order":1,"of":12,"metrics":{"mean Corruption Error (mCE)":"92.55%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.02605","atlas_url":"https://app.syntology.ai/?focus=2207.02605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}