Sparse Coding Approach for Multi-Frame Image Super Resolution

TL;DR

This paper introduces a sparse coding-based multi-frame super-resolution method that accurately estimates displacements and adaptively selects informative patches, outperforming conventional methods on real-world datasets.

Contribution

It presents a novel combination of sub-pixel block matching and sparse signal representation for improved multi-frame super-resolution.

Findings

Achieves comparable or superior results to existing methods.

Efficiently estimates relative displacements for high-quality reconstruction.

Works effectively even with a single low-resolution image.

Abstract

An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative displacements of observed images, and sparse signal representation for estimating the corresponding high-resolution image. Relative displacements of small patches of observed low-resolution images are accurately estimated by a computationally efficient block matching method. Since the estimated displacements are also regarded as a warping component of image degradation process, the matching results are directly utilized to generate low-resolution dictionary for sparse image representation. The matching scores of the block matching are used to select a subset of low-resolution patches for reconstructing a high-resolution patch, that is, an adaptive selection of informative low-resolution images is realized. When there is only one low-resolution image, the proposed method works as a single-frame super-resolution method. The proposed method is shown to perform comparable or superior to conventional single- and multi-frame super-resolution methods through experiments using various real-world datasets.