Range image super-resolution via reconstruction of sparse range data

Abstract

We propose a method for super-resolution of range image. Our approach leverages the interpretation of LR image as sparse samples on the HR grid. Based on this interpretation, we build upon a recent approach which reconstructs dense range images from sparse range data. We notice certain shortcomings of this approach and propose some improvements, particularly, to address the super-resolution problem. Our method only uses a single colour image in addition to the range observation in the super-resolution process. Using the proposed approach, we demonstrate super-resolution results for large factors (e.g. 4 and 8) with good localization and accuracy.