Monocular depth estimation, which plays a key role in understanding 3D scene
geometry, is fundamentally an ill-posed problem. Existing methods based on deep
convolutional neural networks (DCNNs) have examined this problem by learning
convolutional networks to estimate continuous depth maps from monocular images.
However, we find that training a network to predict a high spatial resolution
continuous depth map often suffers from poor local solutions. In this paper, we
hypothesize that achieving a compromise between spatial and depth resolutions
can improve network training. Based on this "compromise principle", we propose
a regression-classification cascaded network (RCCN), which consists of a
regression branch predicting a low spatial resolution continuous depth map and
a classification branch predicting a high spatial resolution discrete depth
map. The two branches form a cascaded structure allowing the classification and
regression branches to benefit from each other. By leveraging large-scale raw
training datasets and some data augmentation strategies, our network achieves
top or state-of-the-art results on the NYU Depth V2, KITTI, and Make3D
benchmarks.

本文提出了一种基于回归和分类级联的网络，利用大规模训练数据和数据增强策略，在空间和深度分辨率之间寻求平衡，提高了网络的训练效果，在 NYU Depth V2、KITTI、Make3D 等基准测试中均取得了最佳或最先进的结果。