RDRN: Recursively Defined Residual Network for Image Super-Resolution

TL;DR

The paper introduces RDRN, a novel deep CNN architecture with recursively defined residual blocks that enhances feature propagation and attention efficiency, achieving state-of-the-art results in single image super-resolution.

Contribution

It proposes a new recursively defined residual block and network architecture that improves feature extraction and attention utilization in image super-resolution.

Findings

Achieves state-of-the-art super-resolution performance.

Outperforms previous methods by up to 0.43 dB.

Effective in training very deep networks for SISR.

Abstract

Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution (SISR). However, very deep networks can suffer from training difficulty and hardly achieve further performance gain. There are two main trends to solve that problem: improving the network architecture for better propagation of features through large number of layers and designing an attention mechanism for selecting most informative features. Recent SISR solutions propose advanced attention and self-attention mechanisms. However, constructing a network to use an attention block in the most efficient way is a challenging problem. To address this issue, we propose a general recursively defined residual block (RDRB) for better feature extraction and propagation through network layers. Based on RDRB we designed recursively defined residual network (RDRN), a novel network architecture which utilizes attention blocks efficiently. Extensive experiments show that the proposed model achieves state-of-the-art results on several popular super-resolution benchmarks and outperforms previous methods by up to 0.43 dB.