Variable Bandwidth Weighting for Texture Copy Artifact Suppression in Guided Depth Upsampling

In this paper, we mathematically analyze one of the most challenging issues in color image-guided depth upsampling: the texture copy artifacts. The optimal guidance weights denoted by balanced weights are proposed to best suppress texture copy artifacts. To both suppress texture copy artifacts and preserve depth discontinuities, a new general weighting scheme called variable bandwidth weighting is proposed. The variable bandwidth weighting scheme is able to adjust guidance weights according to the local depth smoothness. A new concept called relative smoothness is proposed for measuring the local depth smoothness. Given this quantitative smoothness measurement, the proposed weighting scheme can adaptively adjust the bandwidth for calculating the guidance weights in the existing methods. As we use the computationally efficient balanced weights instead of the guidance weights of a large bandwidth, the proposed method can speed up the upsampling process for about $2\times \sim 5\times $ when compared with the original upsampling methods. Experimental results show the effectiveness and efficiency of the proposed method in suppressing texture copy artifacts, preserving the depth discontinuities and reducing the computational cost at the same time.