RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation

Li, L.; Shum, H. P. H.; Breckon, T. P.

Abstract

3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets.

Citation

Li, L., Shum, H. P. H., & Breckon, T. P. (2024, September). RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation. Presented at ECCV 2024: European Conference on Computer Vision, Milan, Italy

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ECCV 2024: European Conference on Computer Vision
• Start Date: Sep 29, 2024
• End Date: Oct 5, 2024
• Acceptance Date: Jun 1, 2024
• Online Publication Date: Sep 29, 2024
• Publication Date: Jan 1, 2025
• Deposit Date: Jul 23, 2024
• Publicly Available Date: Sep 29, 2024
• Journal: European Conference on Computer Vision (ECCV)
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 15065 LNCS
• Pages: 222-241
• Series Title: Lecture Notes in Computer Science
• Series ISSN: 0302-9743
• Book Title: Computer Vision – ECCV 2024
• DOI: https://doi.org/10.1007/978-3-031-72667-5_13
• Keywords: autonomous driving, LiDAR, semantic segmentation, 3D feature points
• Public URL: https://durham-repository.worktribe.com/output/2610751
• Related Public URLs: https://breckon.org/toby/publications/papers/li24rapid-seg.pdf