3D visual perception tasks based on multi-camera images are essential for autonomous driving systems. Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object queries (object proposals) by cross-attending multi-view features. However, individual backbone features are not updated with multi-view features and it stays as a mere collection of the output of the single-image backbone network. Therefore we propose 3M3D: A Multi-view, Multi-path, Multi-representation for 3D Object Detection where we update both multi-view features and query features to enhance the representation of the scene in both fine panoramic view and coarse global view. Firstly, we update multi-view features by multi-view axis self-attention. It will incorporate panoramic information in the multi-view features and enhance understanding of the global scene. Secondly, we update multi-view features by self-attention of the ROI (Region of Interest) windows which encodes local finer details in the features. It will help exchange the information not only along the multi-view axis but also along the other spatial dimension. Lastly, we leverage the fact of multi-representation of queries in different domains to further boost the performance. Here we use sparse floating queries along with dense BEV (Bird's Eye View) queries, which are later post-processed to filter duplicate detections. Moreover, we show performance improvements on nuScenes benchmark dataset on top of our baselines.

翻译：基于多相机图像的三维视觉感知任务对自动驾驶系统至关重要。该领域的最新工作通过利用多视图图像作为输入，并借助跨注意力机制迭代增强目标查询（目标提议）与多视图特征的交互来实现3D物体检测。然而，各主干网络的特征并未随多视图特征进行更新，仍只是单图像主干网络输出的简单集合。为此，我们提出3M3D：一种面向3D物体检测的多视图、多路径、多表示方法，该方法同步更新多视图特征与查询特征，以增强场景在精细全景视图和粗略全局视图中的表示。首先，通过多视图轴向自注意力机制更新多视图特征，将全景信息融入多视图特征以增强全局场景理解。其次，利用感兴趣区域（ROI）窗口的自注意力更新多视图特征，编码特征中的局部细节信息，这不仅能在多视图轴向传递信息，还能沿其他空间维度进行信息交换。最后，利用查询在不同域中的多表示特性进一步提升性能：结合稀疏浮点查询与密集鸟瞰图（BEV）查询，并通过后处理过滤重复检测结果。此外，我们在nuScenes基准数据集上展现了相较于基线方法的性能提升。