Single depth map super-resolution via joint non-local and local modeling

Recently, consumer depth cameras have gained significant popularity due to their affordable cost. However, the resolution and the quality of the depth map generated by these cameras are limited, which affects its application performance. In this paper, we propose a novel framework for the single depth map super-resolution via joint the local and non-local constraints simultaneously in the depth map. For the non-local constraint, we use the group-based sparse representation to explore the nonlocal self-similarity of depth map. For the local constraint, we first estimate gradient images in different directions of the desired high-resolution (HR) depth map, and then build multi-directional gradient guided regularizer using these estimated gradient images to characterize depth gradients with spatially-varying orientations. Finally, the two complementary regularizers are cast into a unified optimization framework to obtain the desired HR image. Quantitative and qualitative evaluations compared with state-ofthe-art methods demonstrate that the proposed method achieves superior depth super-resolution performance.