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.