AI RESEARCH

RadarGaussianDet3D: Gaussian Representation-based Real-time 3D Object Detection with 4D Automotive Radars

arXiv CS.CV

ArXi:2509.16119v2 Announce Type: replace 4D automotive radars have gained increasing attention for autonomous driving due to their low cost, robustness, and inherent velocity measurement capability. However, existing 4D radar-based 3D detectors rely heavily on pillar encoders for BEV feature extraction, where each point contributes to only a single BEV grid, resulting in sparse feature maps and degraded representation quality. In addition, they also optimize bounding box attributes independently, leading to sub-optimal detection accuracy.