Blueprint Separable Residual Network for Efficient Image Super-Resolution
This work addresses the need for efficient super-resolution models for deployment on edge devices, representing an incremental improvement over existing efficient methods.
The paper tackles the problem of high computational cost in single image super-resolution (SISR) for edge devices by proposing the Blueprint Separable Residual Network (BSRN), which uses blueprint separable convolution and enhanced attention modules to achieve state-of-the-art performance among efficient SR methods, with a smaller variant winning first place in the NTIRE 2022 Efficient SR Challenge.
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.