Blueprint Separable Residual Network for Efficient Image Super-Resolution

TL;DR

The paper introduces BSRN, a novel neural network architecture for image super-resolution that reduces computational redundancy and enhances efficiency, achieving state-of-the-art results and winning a challenge.

Contribution

The paper proposes Blueprint Separable Residual Network (BSRN) with blueprint separable convolution and improved attention modules for efficient super-resolution.

Findings

BSRN achieves state-of-the-art performance among efficient SR methods.

BSRN-S wins first place in NTIRE 2022 Efficient SR Challenge.

The model reduces computational cost while maintaining high accuracy.

Abstract

Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply in edge devices. To alleviate this problem, many novel and effective solutions have been proposed. Convolutional neural network (CNN) with the attention mechanism has attracted increasing attention due to its efficiency and effectiveness. However, there is still redundancy in the convolution operation. In this paper, we propose Blueprint Separable Residual Network (BSRN) containing two efficient designs. One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation. The other is to enhance the model ability by introducing more effective attention modules. The experimental results show that BSRN achieves state-of-the-art performance among existing efficient SR methods. Moreover, a smaller variant of our model BSRN-S won the first place in model complexity track of NTIRE 2022 Efficient SR Challenge. The code is available at https://github.com/xiaom233/BSRN.