Image hallucination with feature enhancement

Example-based super-resolution recovers missing high frequencies in a magnified image by learning the corres-pondence between co-occurrence examples at two differ-ent resolution levels. As high-resolution examples usually contain more details and are of higher dimensionality in comparison with low-resolution ones, the mapping from low-resolution to high-resolution is an ill-posed problem. Rather than imposing more complicated mapping con-straints, we propose to improve the mapping accuracy by enhancing low-resolution examples in terms of mapped features, e.g., derivatives and primitives. A feature en-hancement method is presented through a combination of interpolation with prefiltering and non-blind sparse prior deblurring. By enhancing low-resolution examples, unique feature information carried by high-resolution examples is decreased. This regularization reduces the intrinsic di-mensionality disparity between two different resolution examples and thus improves the feature mapping accura-cy. Experiments demonstrate our super-resolution scheme with feature enhancement produces high quality results both perceptually and quantitatively.