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. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Depth restoration, super-resolution, denoising, graph signal processing |
Field | DocType | ISSN |
Computer vision,Laplacian matrix,Task analysis,Computer science,Fourier transform,Plug and play,Artificial intelligence,Image restoration,Rendering (computer graphics),Convex optimization,Image resolution | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rong Chen | 1 | 55 | 10.48 |
Deming Zhai | 2 | 141 | 13.44 |
Xianming Liu | 3 | 461 | 47.55 |
Debin Zhao | 4 | 3010 | 206.12 |