Depth Map Upsampling via Compressive Sensing

We propose a new method to enhance the lateral resolution of depth maps with registered high-resolution color images. Inspired by the theory of Compressive Sensing (CS), we formulate the up sampling task as a sparse signal recovery problem. With a reference color image, the low-resolution depth map is converted into suitable sampling data (measurements). The signal recovery problem, defined in a constrained optimization framework, can be efficiently solved with variable splitting and alternating minimization. Experimental results demonstrate the effectiveness of our CS-based method: it competes favorably with other state-of-the-art methods with large up sampling factors and noisy depth inputs.