Multi-Scale Frequency Reconstruction for Guided Depth Map Super-Resolution via Deep Residual Network | doi.page

0 citations0 references

Multi-Scale Frequency Reconstruction for Guided Depth Map Super-Resolution via Deep Residual Network

IEEE Transactions on Circuits and Systems for Video Technology2019Vol. 30(2), pp. 297–306

Citations Over TimeTop 10% of 2019 papers

Yifan Zuo, Qiang Wu, Yuming Fang, Ping An, Liqin Huang, Zhifeng Chen

Abstract

The depth maps obtained by the consumer-level sensors are always noisy in the low-resolution (LR) domain. Existing methods for the guided depth super-resolution, which are based on the pre-defined local and global models, perform well in general cases (e.g., joint bilateral filter and Markov random field). However, such model-based methods may fail to describe the potential relationship between RGB-D image pairs. To solve this problem, this paper proposes a data-driven approach based on the deep convolutional neural network with global and local residual learning. It progressively upsamples the LR depth map guided by the high-resolution intensity image in multiple scales. A global residual learning is adopted to learn the difference between the ground truth and the coarsely upsampled depth map, and the local residual learning is introduced in each scale-dependent reconstruction sub-network. This scheme can restore the depth structure from coarse to fine via multi-scale frequency synthesis. In addition, batch normalization layers are used to improve the performance of depth map denoising. Our method is evaluated in noise-free and noisy cases. A comprehensive comparison against 17 state-of-the-art methods is carried out. The experimental results show that the proposed method has faster convergence speed as well as improved performances based on the qualitative and quantitative evaluations.

Citations Over TimeTop 10% of 2019 papers

Abstract

Related Papers