Exploiting Non-Local Priors via Self-Convolution For Highly-Efficient Image Restoration

TL;DR

This paper introduces Self-Convolution, a novel operator that efficiently exploits non-local image similarity, significantly speeding up image restoration algorithms and improving denoising performance on multi-modality images.

Contribution

The paper proposes Self-Convolution, a new method that replaces traditional block matching, enabling faster and more effective non-local image restoration.

Findings

Self-Convolution speeds up non-local algorithms by 2-9 times.

The multi-modality restoration scheme outperforms conventional methods in efficiency.

Achieves superior denoising results on RGB-NIR images.

Abstract

Constructing effective image priors is critical to solving ill-posed inverse problems in image processing and imaging. Recent works proposed to exploit image non-local similarity for inverse problems by grouping similar patches and demonstrated state-of-the-art results in many applications. However, compared to classic methods based on filtering or sparsity, most of the non-local algorithms are time-consuming, mainly due to the highly inefficient and redundant block matching step, where the distance between each pair of overlapping patches needs to be computed. In this work, we propose a novel Self-Convolution operator to exploit image non-local similarity in a self-supervised way. The proposed Self-Convolution can generalize the commonly-used block matching step and produce equivalent results with much cheaper computation. Furthermore, by applying Self-Convolution, we propose an effective multi-modality image restoration scheme, which is much more efficient than conventional block matching for non-local modeling. Experimental results demonstrate that (1) Self-Convolution can significantly speed up most of the popular non-local image restoration algorithms, with two-fold to nine-fold faster block matching, and (2) the proposed multi-modality image restoration scheme achieves superior denoising results in both efficiency and effectiveness on RGB-NIR images. The code is publicly available at \href{https://github.com/GuoLanqing/Self-Convolution}.