Efficient Non-local Contrastive Attention for Image Super-resolution

Single-image super-resolution via local learning

Nearest neighbor-based algorithms are popular in example-based super-resolution from a single image. The core idea behind such algorithms is that similar images are close in the sense of distance measurement. However, it is well known in the field of machine learning and statistical learning theory that the generalization of the nearest neighbor-based estimation is poor, when complex or high di...

Efficient image warping and super-resolution

Local Patch Classification Based Framework for Single Image Super-Resolution

methods often focus on the dictionary learning or network training. In this paper, we detailedly discuss a new SR framework based on local classification instead of traditional dictionary learning. The proposed efficient and extendible SR framework is named as local patch classification (LPC) based framework. The LPC framework consists of a learning stage and a reconstructing stage. In the lear...

Non-Local Contrastive Objectives

Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabilities of other “nearby” instantiations. In this paper we explore more general types of contrastive objectives, which trade off the probability of the correct label against an arbitrary set of other instantiations. We pr...

Single-Image Super-Resolution Using Sparsity Constraints and Non-Local Similarities at Multiple Resolution Scales

Traditional super-resolution methods produce a clean high-resolution image from several observed degraded low-resolution images following an acquisition or degradation model. Such a model describes how each output pixel is related to one or more input pixels and it is called data fidelity term in the regularization framework. Additionally, prior knowledge such as piecewise smoothness can be inc...