2025/04/23 by Linhua Kong, Kong, Linhua, Dongxia Chang +9
Engineering · #Advanced SAR Imaging Techniques #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Feature (linguistics) #Feature extraction #Fuse (electrical) #Infrared Target Detection Methodologies #Object (grammar) #Object detection #Radar #Radar engineering details #Radar imaging #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.2504.16368
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/04/23 · openalex created_date 2025/10/11 · openalex updated_date 2026/08/05
Recently, 3D object detection algorithms based on radar and camera fusion have shown excellent performance, setting the stage for their application in autonomous driving perception tasks. Existing methods have focused on dealing with feature misalignment caused by the domain gap between radar and camera. However, existing methods either neglect inter-modal features interaction during alignment or fail to effectively align features at the same spatial location across modalities. To alleviate the above problems, we propose a new alignment model called Radar Camera Alignment (RCAlign). Specifically, we design a Dual-Route Alignment (DRA) module based on contrastive learning to align and fuse the features between radar and camera. Moreover, considering the sparsity of radar BEV features, a Radar Feature Enhancement (RFE) module is proposed to improve the densification of radar BEV features with the knowledge distillation loss. Experiments show RCAlign achieves a new state-of-the-art on the public nuScenes benchmark in radar camera fusion for 3D Object Detection. Furthermore, the RCAlign achieves a significant performance gain (4.3% NDS and 8.4% mAP) in real-time 3D detection compared to the latest state-of-the-art method (RCBEVDet).