{"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/fg-net-fast-large-scale-lidar-point","title":"FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling","arxiv_id":"2012.09439","date":"2020-12-17","proceeding":null,"authors":["Kangcheng Liu","Zhi Gao","Feng Lin","Ben M. Chen"],"abstract":"This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU. First, a novel noise and outlier filtering method is designed to facilitate subsequent high-level tasks. For effective understanding purpose, we propose a deep convolutional neural network leveraging correlated feature mining and deformable convolution based geometric-aware modelling, in which the local feature relationships and geometric patterns can be fully exploited. For the efficiency issue, we put forward an inverse density sampling operation and a feature pyramid based residual learning strategy to save the computational cost and memory consumption respectively. Extensive experiments on real-world challenging datasets demonstrated that our approaches outperform state-of-the-art approaches in terms of accuracy and efficiency. Moreover, weakly supervised transfer learning is also conducted to demonstrate the generalization capacity of our method.","url_abs":"https://arxiv.org/abs/2012.09439v2","url_pdf":"https://arxiv.org/pdf/2012.09439v2.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":"fg-net-fast-large-scale-lidar-point","repo_url":"https://github.com/KangchengLiu/Feature-Geometric-Net-FG-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"weakly-supervised-segmentation","task_name":"Weakly supervised segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deformable-convolution","method_name":"Deformable Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"Feature Geometric Net (FG-Net)","rank_in_archive_order":17,"of":67,"metrics":{"Class Average IoU":"87.7","Instance Average IoU":"86.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Feature Geometric Net (FG-Net)","rank_in_archive_order":40,"of":111,"metrics":{"Mean Accuracy":"91.1","Overall Accuracy":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-partnet","task":"3D Semantic Segmentation","dataset":"PartNet","model":"FG-Net","rank_in_archive_order":3,"of":6,"metrics":{"mIOU":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"FG-Net","rank_in_archive_order":31,"of":45,"metrics":{"test mIoU":"53.8%"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-paris-lille-3d","task":"LIDAR Semantic Segmentation","dataset":"Paris-Lille-3D","model":"Feature Geometric Net (FG Net)","rank_in_archive_order":2,"of":9,"metrics":{"mIOU":"0.819"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"Feature Geometric Net (FG-Net)","rank_in_archive_order":21,"of":54,"metrics":{"Mean IoU":"70.8","Number of params":"N/A","mAcc":"82.9","oAcc":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannet","task":"Semantic Segmentation","dataset":"ScanNet","model":"FG-Net","rank_in_archive_order":34,"of":45,"metrics":{"test mIoU":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-semantic3d","task":"Semantic Segmentation","dataset":"Semantic3D","model":"Feature Geometric Net","rank_in_archive_order":1,"of":17,"metrics":{"mIoU":"78.2%","oAcc":"93.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.09439","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}