RV-FuseNet: Range View Based Fusion of Time-Series LiDAR Data for Joint 3D Object Detection and Motion Forecasting
This addresses the need for robust real-time perception in autonomous vehicles, representing an incremental advance by optimizing fusion for range view representations.
The paper tackles the problem of joint 3D object detection and motion forecasting from time-series LiDAR data for autonomous vehicles, proposing RV-FuseNet with an Incremental Fusion architecture that significantly improves motion forecasting performance over state-of-the-art methods.
Robust real-time detection and motion forecasting of traffic participants is necessary for autonomous vehicles to safely navigate urban environments. In this paper, we present RV-FuseNet, a novel end-to-end approach for joint detection and trajectory estimation directly from time-series LiDAR data. Instead of the widely used bird's eye view (BEV) representation, we utilize the native range view (RV) representation of LiDAR data. The RV preserves the full resolution of the sensor by avoiding the voxelization used in the BEV. Furthermore, RV can be processed efficiently due to its compactness. Previous approaches project time-series data to a common viewpoint for temporal fusion, and often this viewpoint is different from where it was captured. This is sufficient for BEV methods, but for RV methods, this can lead to loss of information and data distortion which has an adverse impact on performance. To address this challenge we propose a simple yet effective novel architecture, \textit{Incremental Fusion}, that minimizes the information loss by sequentially projecting each RV sweep into the viewpoint of the next sweep in time. We show that our approach significantly improves motion forecasting performance over the existing state-of-the-art. Furthermore, we demonstrate that our sequential fusion approach is superior to alternative RV based fusion methods on multiple datasets.