High Quality Monocular Depth Estimation Via A Multi-Scale Network And A Detail-Preserving Objective
Hualie Jiang, Rui Huang · 2019
Monocular depth estimation is an important and challenging task in computer vision. Significant progress has been made recently due to deep convolutional neural networks. However, esitmating depth maps with high quality lacks sufficient attention. This paper proposes to recover detailed depth map by training a multi-scale network architecture with a detailpreserving loss function. Firstly, we construct our architecture inspired by the design of atrous spatial pyramid pooling for semantic segmentation. Secondly, we simplify the loss on depth map gradients for preserving details. Experiments on the NYU Depth V2 dataset show that our approach is effective and it achieves state-of-the-art performance, especially in the root mean squared error.