Efficient Image Super-Resolution via Symmetric Visual Attention Network

TL;DR

This paper introduces the Symmetric Visual Attention Network (SVAN), a novel efficient super-resolution model that achieves high-quality results with significantly fewer parameters by leveraging large receptive fields and attention mechanisms.

Contribution

The paper proposes a new SVAN architecture that combines large receptive fields with an attention mechanism, reducing parameters while enhancing super-resolution quality.

Findings

SVAN achieves high-quality super-resolution with only 30% of the parameters of state-of-the-art methods.

The symmetric large kernel attention block effectively captures detailed features.

The model demonstrates improved perceptual quality in reconstructed images.

Abstract

An important development direction in the Single-Image Super-Resolution (SISR) algorithms is to improve the efficiency of the algorithms. Recently, efficient Super-Resolution (SR) research focuses on reducing model complexity and improving efficiency through improved deep small kernel convolution, leading to a small receptive field. The large receptive field obtained by large kernel convolution can significantly improve image quality, but the computational cost is too high. To improve the reconstruction details of efficient super-resolution reconstruction, we propose a Symmetric Visual Attention Network (SVAN) by applying large receptive fields. The SVAN decomposes a large kernel convolution into three different combinations of convolution operations and combines them with an attention mechanism to form a Symmetric Large Kernel Attention Block (SLKAB), which forms a symmetric attention block with a bottleneck structure by the size of the receptive field in the convolution combination to extract depth features effectively as the basic component of the SVAN. Our network gets a large receptive field while minimizing the number of parameters and improving the perceptual ability of the model. The experimental results show that the proposed SVAN can obtain high-quality super-resolution reconstruction results using only about 30% of the parameters of existing SOTA methods.