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.

翻译：近年来，基于LSS的多视图三维目标检测通过卷积检测器处理鸟瞰图（BEV）特征取得了巨大进展。然而，标准卷积忽略了BEV特征的径向对称性，增加了检测器优化的难度。为保留BEV特征的固有特性并简化优化过程，我们提出方位等变卷积（AeConv）和方位等变锚点。AeConv的采样网格始终沿径向方向，因此能够学习方位不变的BEV特征。所提出的锚点使检测头能够学习预测与方位无关的目标。此外，我们引入相机解耦的虚拟深度，统一不同内参相机图像的深度预测。由此得到的检测器称为方位等变检测器（AeDet）。在nuScenes上的大量实验表明，AeDet达到了62.0%的NDS，大幅超越了PETRv2和BEVDepth等最新的多视图三维目标检测方法。项目页面：https://fcjian.github.io/aedet。