TV-based multi-scale super resolution using intra- and inter-scale correlations

A multi-scale approach is proposed in this paper for image super resolution (SR) from a single source image of a low resolution (LR). In this approach, a sequence of "coarse" SR images, called multi-scales, are first generated from the source image via a total variation (TV) based restoration scheme. All multi-scale images are then brought into the minimum mean-square-error (MMSE) estimation to compose the final SR image. We demonstrate that these multi-scale images contain some geometric information and are highly correlated with each other. Therefore, by making use of intra- and inter-scale correlations, the joint MMSE estimation is able to produce a better quality (both objective and subjective) in the composed SR image. Experimental results are provided to confirm the performance gain over several state-of-the-art methods.