Predicting depth is an essential component in understanding the 3D geometry
of a scene. While for stereo images local correspondence suffices for
estimation, finding depth relations from a single image is less
straightforward, requiring integration of both global and local information
from various cues. Moreover, the task is inherently ambiguous, with a large
source of uncertainty coming from the overall scale. In this paper, we present
a new method that addresses this task by employing two deep network stacks: one
that makes a coarse global prediction based on the entire image, and another
that refines this prediction locally. We also apply a scale-invariant error to
help measure depth relations rather than scale. By leveraging the raw datasets
as large sources of training data, our method achieves state-of-the-art results
on both NYU Depth and KITTI, and matches detailed depth boundaries without the
need for superpixelation.

本文提出了一种新的方法，利用两个深度网络堆栈来解决单张图像深度估计的问题，并应用尺度不变误差来测量深度关系，通过利用原始数据集作为大量训练数据，方法在 NYU Depth 和 KITTI 上实现了最先进的结果。