PersDet: Monocular 3D Detection in Perspective Bird's-Eye-View
This addresses deployment challenges for autonomous driving and robotics by enabling efficient 3D detection on edge devices, though it is incremental as it builds on the BEV paradigm.
The paper tackles the problem of deploying 3D object detectors in Bird's-Eye-View (BEV) on edge devices by proposing a new perspective BEV representation that eliminates the need for feature sampling, which is unsupported on many such devices. PersDet, their method, achieves 34.6% mAP and 40.8% NDS on the nuScenes benchmark, outperforming existing state-of-the-art monocular methods.
Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These operators are not supported on many edge devices, bringing extra obstacles when deploying detectors. To address this problem, we revisit the generation of BEV representation and propose detecting objects in perspective BEV -- a new BEV representation that does not require feature sampling. We demonstrate that perspective BEV features can likewise enjoy the benefits of the BEV paradigm. Moreover, the perspective BEV improves detection performance by addressing issues caused by feature sampling. We propose PersDet for high-performance object detection in perspective BEV space based on this discovery. While implementing a simple and memory-efficient structure, PersDet outperforms existing state-of-the-art monocular methods on the nuScenes benchmark, reaching 34.6% mAP and 40.8% NDS when using ResNet-50 as the backbone.