Deep Depth Super-Resolution : Learning Depth Super-Resolution using Deep Convolutional Neural Network

TL;DR

This paper introduces a deep learning approach for depth image super-resolution that combines neural networks with depth and color priors, significantly improving resolution quality over existing methods.

Contribution

It extends deep convolutional neural networks to depth super-resolution by integrating depth field statistics and color-depth correlation in an energy minimization framework.

Findings

Outperforms state-of-the-art depth super-resolution methods

Effective use of depth and color priors improves results

Demonstrates robustness across various benchmark datasets

Abstract

Depth image super-resolution is an extremely challenging task due to the information loss in sub-sampling. Deep convolutional neural network have been widely applied to color image super-resolution. Quite surprisingly, this success has not been matched to depth super-resolution. This is mainly due to the inherent difference between color and depth images. In this paper, we bridge up the gap and extend the success of deep convolutional neural network to depth super-resolution. The proposed deep depth super-resolution method learns the mapping from a low-resolution depth image to a high resolution one in an end-to-end style. Furthermore, to better regularize the learned depth map, we propose to exploit the depth field statistics and the local correlation between depth image and color image. These priors are integrated in an energy minimization formulation, where the deep neural network learns the unary term, the depth field statistics works as global model constraint and the color-depth correlation is utilized to enforce the local structure in depth images. Extensive experiments on various depth super-resolution benchmark datasets show that our method outperforms the state-of-the-art depth image super-resolution methods with a margin.