Single-Image Depth Estimation Based on Fourier Domain Analysis

Jae-Han Lee, Minhyeok Heo, Kyung-Rae Kim, Chang-Su Kim; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 330-339

We propose a deep learning algorithm for single-image depth estimation based on the Fourier frequency domain analysis. First, we develop a convolutional neural network structure and propose a new loss function, called depth-balanced Euclidean loss, to train the network reliably for a wide range of depths. Then, we generate multiple depth map candidates by cropping input images with various cropping ratios. In general, a cropped image with a small ratio yields depth details more faithfully, while that with a large ratio provides the overall depth distribution more reliably. To take advantage of these complementary properties, we combine the multiple candidates in the frequency domain. Experimental results demonstrate that proposed algorithm provides the state-of-art performance. Furthermore, through the frequency domain analysis, we validate the efficacy of the proposed algorithm in most frequency bands.