Demosaicing and Superresolution for Color Filter Array via Residual Image Reconstruction and Sparse Representation

TL;DR

This paper introduces a novel framework combining residual image reconstruction and sparse representation to enhance demosaicing and superresolution of color filter array images, resulting in images with richer details and edges.

Contribution

It proposes a new method that learns generic and adaptive dictionaries for residual image reconstruction, improving image quality over existing techniques.

Findings

Achieves state-of-the-art PSNR performance.

Produces images with richer edges and details.

Demonstrates superior subjective visual quality.

Abstract

A framework of demosaicing and superresolution for color filter array (CFA) via residual image reconstruction and sparse representation is presented.Given the intermediate image produced by certain demosaicing and interpolation technique, a residual image between the final reconstruction image and the intermediate image is reconstructed using sparse representation.The final reconstruction image has richer edges and details than that of the intermediate image. Specifically, a generic dictionary is learned from a large set of composite training data composed of intermediate data and residual data. The learned dictionary implies a mapping between the two data. A specific dictionary adaptive to the input CFA is learned thereafter. Using the adaptive dictionary, the sparse coefficients of intermediate data are computed and transformed to predict residual image. The residual image is added back into the intermediate image to obtain the final reconstruction image. Experimental results demonstrate the state-of-the-art performance in terms of PSNR and subjective visual perception.