论文标题
AEDET：方位角不变的多视图3D对象检测
AeDet: Azimuth-invariant Multi-view 3D Object Detection
论文作者
论文摘要
最近基于LSS的多视图3D对象检测通过卷积检测器处理Brid-Eye-View（BEV）中的功能，从而取得了巨大进步。但是，典型的卷积忽略了BEV特征的径向对称性，并增加了检测器优化的难度。为了保留BEV特征的固有特性并简化优化，我们提出了方位角 - 等级卷积（AECONV）和方位角 - 均等锚。 AECONV的采样网格始终朝着径向方向，因此可以学习方位角不变的BEV特征。所提出的锚使检测头能够学习预测方位角 - 毫优化目标。此外，我们引入了一个摄像机耦合的虚拟深度，以统一具有不同摄像机固有参数的图像的深度预测。所得检测器被称为方位角 - 等级探测器（AEDET）。大量实验是在Nuscenes上进行的，AEDET达到了62.0％的NDS，超过了最近的多视图3D对象检测器，例如PETRV2和BEVDEPTH，并以很大的余量为单位。项目页面：https：//fcjian.github.io/aedet。
Recent LSS-based multi-view 3D object detection has made tremendous progress, by processing the features in Brid-Eye-View (BEV) via the convolutional detector. However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization. To preserve the inherent property of the BEV features and ease the optimization, we propose an azimuth-equivariant convolution (AeConv) and an azimuth-equivariant anchor. The sampling grid of AeConv is always in the radial direction, thus it can learn azimuth-invariant BEV features. The proposed anchor enables the detection head to learn predicting azimuth-irrelevant targets. In addition, we introduce a camera-decoupled virtual depth to unify the depth prediction for the images with different camera intrinsic parameters. The resultant detector is dubbed Azimuth-equivariant Detector (AeDet). Extensive experiments are conducted on nuScenes, and AeDet achieves a 62.0% NDS, surpassing the recent multi-view 3D object detectors such as PETRv2 and BEVDepth by a large margin. Project page: https://fcjian.github.io/aedet.
