Non-Local Recurrent Network for Image Restoration

TL;DR

This paper introduces a non-local recurrent network that effectively captures deep feature correlations for image restoration tasks, achieving superior results with fewer parameters by integrating non-local operations into an RNN framework.

Contribution

It proposes the first non-local recurrent network for image restoration, combining non-local modules with RNNs for improved feature correlation and robustness.

Findings

Outperforms state-of-the-art methods in denoising and super-resolution

Uses fewer parameters than existing models

Maintains robustness against severely degraded images

Abstract

Many classic methods have shown non-local self-similarity in natural images to be an effective prior for image restoration. However, it remains unclear and challenging to make use of this intrinsic property via deep networks. In this paper, we propose a non-local recurrent network (NLRN) as the first attempt to incorporate non-local operations into a recurrent neural network (RNN) for image restoration. The main contributions of this work are: (1) Unlike existing methods that measure self-similarity in an isolated manner, the proposed non-local module can be flexibly integrated into existing deep networks for end-to-end training to capture deep feature correlation between each location and its neighborhood. (2) We fully employ the RNN structure for its parameter efficiency and allow deep feature correlation to be propagated along adjacent recurrent states. This new design boosts robustness against inaccurate correlation estimation due to severely degraded images. (3) We show that it is essential to maintain a confined neighborhood for computing deep feature correlation given degraded images. This is in contrast to existing practice that deploys the whole image. Extensive experiments on both image denoising and super-resolution tasks are conducted. Thanks to the recurrent non-local operations and correlation propagation, the proposed NLRN achieves superior results to state-of-the-art methods with much fewer parameters.