← Back to Benchmarks
simmediumroboticsmetric · varies

Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras

Description

Modern autonomous driving systems increasingly rely on mixed camera configurations with pinhole and fisheye cameras for full view perception. However, Bird's-Eye View (BEV) 3D object detection models are predominantly designed for pinhole cameras, leading to performance degradation under fisheye distortion. To bridge this gap, we introduce a multi-view BEV detection benchmark with mixed cameras by converting KITTI-360 into nuScenes format. Our study encompasses three adaptations: rectification f

Source

http://arxiv.org/abs/2603.27818v1