Uplifting Range-View-based 3D Semantic Segmentation in Real-Time with Multi-Sensor Fusion

TL;DR

This paper introduces LaCRange, a real-time multi-sensor fusion method for 3D semantic segmentation that improves robustness and accuracy by addressing projection distortions and limited resolution issues.

Contribution

The paper proposes a novel multi-sensor fusion approach with distortion compensation, context-based feature fusion, and point refinement for enhanced 3D segmentation.

Findings

Achieves state-of-the-art results on nuScenes dataset

Operates in real-time for autonomous driving applications

Improves segmentation robustness for occluded points

Abstract

Range-View(RV)-based 3D point cloud segmentation is widely adopted due to its compact data form. However, RV-based methods fall short in providing robust segmentation for the occluded points and suffer from distortion of projected RGB images due to the sparse nature of 3D point clouds. To alleviate these problems, we propose a new LiDAR and Camera Range-view-based 3D point cloud semantic segmentation method (LaCRange). Specifically, a distortion-compensating knowledge distillation (DCKD) strategy is designed to remedy the adverse effect of RV projection of RGB images. Moreover, a context-based feature fusion module is introduced for robust and preservative sensor fusion. Finally, in order to address the limited resolution of RV and its insufficiency of 3D topology, a new point refinement scheme is devised for proper aggregation of features in 2D and augmentation of point features in 3D. We evaluated the proposed method on large-scale autonomous driving datasets \ie SemanticKITTI and nuScenes. In addition to being real-time, the proposed method achieves state-of-the-art results on nuScenes benchmark