Resolution-invariant coding for continuous image super-resolution

The paper presents the resolution-invariant image representation Ya{cyrillic}IIR framework. It applies sparse-coding with multi-resolution codebook to learn resolution-invariant sparse representations of local patches. An input image can be reconstructed to higher resolution at not only discrete integer scales, as that in many existing super-resolution works, but also continuous scales, which functions similar to 2-D image interpolation. The Ya{cyrillic}IIR framework includes the methods of building a multi-resolution bases set from training images, learning the optimal sparse resolution-invariant representation of an image, and reconstructing the missing high-frequency information at continuous resolution level. Both theoretical and experimental validations of the resolution invariance property are presented in the paper. Objective comparison and subjective evaluation show that the Ya{cyrillic}IIR framework based image resolution enhancement method outperforms existing methods in various aspects.