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：最近，基于 LSS 的多视角三维物体检测在通过卷积检测器处理 BEV 中的特征后取得了巨大的进展。然而，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困难度。为了保留 BEV 特征的固有属性并减轻优化，我们提出了一个方位等变卷积（AeConv）和方位等变锚。AeConv 的采样网格总是在径向上，因此它可以学习方位不变的 BEV 特征。所提出的锚点使得检测头能够学习预测方位无关的目标。此外，我们引入了一个与相机解耦的虚拟深度，以统一不同相机内参的图像深度预测。得到的检测器被称为方位等变检测器（AeDet）。在 nuScenes 上进行了广泛的实验，并取得了 62.0% 的 NDS，大大超过了最近的多视角 3D 物体检测器，例如 PETRv2 和 BEVDepth。项目页面：https://fcjian.github.io/aedet。
相关内容
微信扫码咨询专知VIP会员