Perceptually-Inspired and Edge-Directed Color Image Super-Resolution

Abstract

Inspired by multi-scale tensor voting, a computational framework for perceptual grouping and segmentation, we propose an edge-directed technique for color image super-resolution given a single low-resolution color image. Our multi-scale technique combines the advantages of edge-directed, reconstruction-based and learning-based methods, and is unique in two ways. First, we consider simultaneously all the three color channels in our multi-scale tensor voting framework to produce a multi-scale edge representation to guide the process of high-resolution color image reconstruction, which is subject to the back projection constraint. Fine details are inferred without noticeable blurry or ringing artifacts. Second, the inference of high-resolution curves is achieved by multi-scale tensor voting, using the dense voting field as an edge-preserving smoothness prior which is derived geometrically without any time-consuming learning procedure. Qualitative and quantitative results indicate that our method produces convincing results in complex test cases typically used by state-of-the-art image super-resolution techniques.