论文标题
bevdepth：获得多视图3D对象检测的可靠深度
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection
论文作者
论文摘要
在这项研究中，我们提出了一个新的3D对象检测器，具有可信赖的深度估计，称为Bevdepth，用于基于摄像机的鸟类视图（BEV）3D对象检测。我们的工作基于一个关键的观察 - 鉴于深度对于相机3D检测至关重要，最近方法中的深度估计是不足的。我们的bevdepth通过利用明确的深度监督来解决这一问题。还引入了相机意识深度估计模块，以促进深度预测能力。此外，我们设计了一个新颖的深度细化模块，以抵消不精确的特征未侵犯所带来的副作用。 BevDepth在自定义的有效体素集合和多框架机制的帮助下，在具有挑战性的Nuscenes测试套件上实现了新的最先进的60.9％NDS，同时保持了高效率。相机型号的NDS得分首次达到60％。
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. Our work is based on a key observation -- depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%.
