Rank-One Network: An Effective Framework for Image Restoration

TL;DR

This paper introduces a novel framework utilizing rank-one components for image restoration, effectively preserving self-similarity and improving results across various tasks like super-resolution and denoising.

Contribution

The paper proposes a new rank-one decomposition and reconstruction framework that leverages neural network-based projections to enhance image restoration performance.

Findings

Effective for noise-free and realistic super-resolution

Superior performance in color image denoising

Efficient and applicable across multiple restoration tasks

Abstract

The principal rank-one (RO) components of an image represent the self-similarity of the image, which is an important property for image restoration. However, the RO components of a corrupted image could be decimated by the procedure of image denoising. We suggest that the RO property should be utilized and the decimation should be avoided in image restoration. To achieve this, we propose a new framework comprised of two modules, i.e., the RO decomposition and RO reconstruction. The RO decomposition is developed to decompose a corrupted image into the RO components and residual. This is achieved by successively applying RO projections to the image or its residuals to extract the RO components. The RO projections, based on neural networks, extract the closest RO component of an image. The RO reconstruction is aimed to reconstruct the important information, respectively from the RO components and residual, as well as to restore the image from this reconstructed information. Experimental results on four tasks, i.e., noise-free image super-resolution (SR), realistic image SR, gray-scale image denoising, and color image denoising, show that the method is effective and efficient for image restoration, and it delivers superior performance for realistic image SR and color image denoising.