{"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/multi-projection-fusion-for-real-time","title":"Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds","arxiv_id":"2011.01974","date":"2020-11-03","proceeding":null,"authors":["Yara Ali Alnaggar","Mohamed Afifi","Karim Amer","Mohamed ElHelw"],"abstract":"Semantic segmentation of 3D point cloud data is essential for enhanced high-level perception in autonomous platforms. Furthermore, given the increasing deployment of LiDAR sensors onboard of cars and drones, a special emphasis is also placed on non-computationally intensive algorithms that operate on mobile GPUs. Previous efficient state-of-the-art methods relied on 2D spherical projection of point clouds as input for 2D fully convolutional neural networks to balance the accuracy-speed trade-off. This paper introduces a novel approach for 3D point cloud semantic segmentation that exploits multiple projections of the point cloud to mitigate the loss of information inherent in single projection methods. Our Multi-Projection Fusion (MPF) framework analyzes spherical and bird's-eye view projections using two separate highly-efficient 2D fully convolutional models then combines the segmentation results of both views. The proposed framework is validated on the SemanticKITTI dataset where it achieved a mIoU of 55.5 which is higher than state-of-the-art projection-based methods RangeNet++ and PolarNet while being 1.6x faster than the former and 3.1x faster than the latter.","url_abs":"https://arxiv.org/abs/2011.01974v2","url_pdf":"https://arxiv.org/pdf/2011.01974v2.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":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"polarnet","method_name":"PolarNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"MPF","rank_in_archive_order":28,"of":45,"metrics":{"test mIoU":"55.5%"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-semantickitti","task":"LIDAR Semantic Segmentation","dataset":"SemanticKITTI","model":"MPF","rank_in_archive_order":4,"of":4,"metrics":{"mIOU":"55.5%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-3d-semantic-segmentation-on-1","task":"Real-Time 3D Semantic Segmentation","dataset":"SemanticKITTI","model":"MPF","rank_in_archive_order":4,"of":4,"metrics":{"Speed  (FPS)":"20.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.01974","atlas_url":"https://app.syntology.ai/?focus=2011.01974","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}