RayFusion: Ray Fusion Enhanced Collaborative Visual Perception
This addresses sensor limitation problems for autonomous driving systems, though it appears incremental as an enhancement to existing collaborative perception methods.
The paper tackles the problem of depth ambiguity in camera-based collaborative perception for autonomous driving by proposing RayFusion, a ray-based fusion method that uses ray occupancy information from collaborators to reduce redundancy and false positives. Experiments show it consistently outperforms state-of-the-art models, substantially advancing collaborative visual perception performance.
Collaborative visual perception methods have gained widespread attention in the autonomous driving community in recent years due to their ability to address sensor limitation problems. However, the absence of explicit depth information often makes it difficult for camera-based perception systems, e.g., 3D object detection, to generate accurate predictions. To alleviate the ambiguity in depth estimation, we propose RayFusion, a ray-based fusion method for collaborative visual perception. Using ray occupancy information from collaborators, RayFusion reduces redundancy and false positive predictions along camera rays, enhancing the detection performance of purely camera-based collaborative perception systems. Comprehensive experiments show that our method consistently outperforms existing state-of-the-art models, substantially advancing the performance of collaborative visual perception. The code is available at https://github.com/wangsh0111/RayFusion.