Abstract:Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision BEV (bird's-eye-view) detection models is accompanied with enormous parameters and computation, which make them unaffordable on edge devices. To address this problem, in this paper, we propose a structured knowledge distillation framework, aiming to improve the efficiency of modern vision-only BEV detection models. The proposed framework mainly includes: (a) spatial-temporal distillation which distills teacher knowledge of information fusion from different timestamps and views, (b) BEV response distillation which distills teacher response to different pillars, and (c) weight-inheriting which solves the problem of inconsistent inputs between students and teacher in modern transformer architectures. Experimental results show that our method leads to an average improvement of 2.16 mAP and 2.27 NDS on the nuScenes benchmark, outperforming multiple baselines by a large margin.
Abstract:In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View (BEV) 3D object detection. By a thorough analysis of recent approaches, we discover that the depth estimation is implicitly learned without camera information, making it the de-facto fake-depth for creating the following pseudo point cloud. BEVDepth gets explicit depth supervision utilizing encoded intrinsic and extrinsic parameters. A depth correction sub-network is further introduced to counteract projecting-induced disturbances in depth ground truth. To reduce the speed bottleneck while projecting features from image-view into BEV using estimated depth, a quick view-transform operation is also proposed. Besides, our BEVDepth can be easily extended with input from multi-frame. Without any bells and whistles, BEVDepth achieves the new state-of-the-art 60.0% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the performance gap between the camera and LiDAR is largely reduced within 10% NDS.