The ubiquitous multi-camera setup on modern autonomous vehicles provides an opportunity to construct surround-view depth. Existing methods, however, either perform independent monocular depth estimations on each camera or rely on computationally heavy self attention mechanisms. In this paper, we propose a novel guided attention architecture, EGA-Depth, which can improve both the efficiency and accuracy of self-supervised multi-camera depth estimation. More specifically, for each camera, we use its perspective view as the query to cross-reference its neighboring views to derive informative features for this camera view. This allows the model to perform attention only across views with considerable overlaps and avoid the costly computations of standard self-attention. Given its efficiency, EGA-Depth enables us to exploit higher-resolution visual features, leading to improved accuracy. Furthermore, EGA-Depth can incorporate more frames from previous time steps as it scales linearly w.r.t. the number of views and frames. Extensive experiments on two challenging autonomous driving benchmarks nuScenes and DDAD demonstrate the efficacy of our proposed EGA-Depth and show that it achieves the new state-of-the-art in self-supervised multi-camera depth estimation.

翻译：现代自动驾驶车辆普遍采用的多相机配置为构建环视深度提供了可能。然而，现有方法要么对每个相机独立执行单目深度估计，要么依赖计算量巨大的自注意力机制。本文提出一种新型引导注意力架构EGA-Depth，能够同时提升自监督多相机深度估计的效率与精度。具体而言，对于每台相机，我们以其透视视图作为查询，通过交叉参考相邻视图来为该视角提取有效特征。这使得模型仅需在重叠显著的视图间执行注意力机制，从而避免了标准自注意力高昂的计算开销。凭借其高效性，EGA-Depth能够利用更高分辨率的视觉特征，进而提升深度估计精度。同时，由于计算复杂度随视角及帧数线性增长，EGA-Depth可便捷地引入更多历史时刻的帧数据。在nuScenes和DDAD两个具有挑战性的自动驾驶基准数据集上的大量实验表明，所提出的EGA-Depth方法效果显著，实现了自监督多相机深度估计的新一代最优性能。