A Compromise Principle in Deep Monocular Depth Estimation

Understand

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.