Noise-Aware Super-Resolution of Depth Maps Via Graph-Based Plug-And-Play Framework

Rong Chen, Deming Zhai, Xianming Liu, Debin Zhao

Abstract

Depth information is being widely used in many real-world tasks, such as 3DTV, 3D scene reconstruction, multi-view rendering, etc. However, the captured depth maps in practice usually suffer from quality degradations, including low-resolution and noise corruption, which limit their further applications. Noise-aware super-resolution of depth maps is a challenging task and has received increasingly more attention in recent years. In this paper, we propose a novel method based on the plug-and-play scheme, which casts two powerful graph-based tools-the graph Laplacian regularizer and 3D graph Fourier transform-into a unified ADMM optimization framework. It can be performed in an iterative manner with easily treatable convex optimization sub-problems. Experiments results demonstrate that our method achieves superior performance compared with the state-of-the-art works with respect to both objective and subjective quality evaluations.
BibTeX
@inproceedings{chen2018noise,
  author = {Rong Chen and Deming Zhai and Xianming Liu and Debin Zhao},
  title = {{Noise-Aware Super-Resolution of Depth Maps Via Graph-Based Plug-And-Play Framework}},
  booktitle = {ICIP},
  year = {2018},
  doi = {10.1109/icip.2018.8451148},
}

Loading related content...

Figure