Optimal Deep Multi-Route Self-Attention for Single Image Super-Resolution

Abstract

Image restoration, such as single image super-resolution (SISR), is a long-established low-level vision issue that intends to regenerate high-resolution (HR) images from low-resolution (LR) input counterparts. While state-of-the-art image super-resolution models are based on the well-known convolutional neural network (CNN), many self-attention-based or transformer-based experiment attempts have been conducted and have shown promising performance on vision problems. A powerful baseline model based on the swin transformer adopts the shifted window approach. It enhances the capability by restricting the model to compute the self-attention function only on non-superimpose local windows while enabling cross-window relations. However, the architecture design is manually fixed. Therefore, the results are not achieving optimal performance. This paper presents an optimal deep multi-route self-attention network for single image super-resolution (ODMR-SASR). The genetic algorithm (GA) is introduced to discover the optimal number of filters and layers. Experimental results demonstrate that the proposed optimization technique can produce a progressive SR image quality.