HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution

TL;DR

HMANet is a novel hybrid transformer network that combines multi-axis aggregation with a pre-training method to significantly improve image super-resolution performance over existing methods.

Contribution

The paper introduces HMANet, a hybrid architecture combining Residual Hybrid Transformer Blocks and Grid Attention Blocks, with a new pre-training strategy for enhanced super-resolution.

Findings

HMANet outperforms state-of-the-art super-resolution methods on benchmark datasets.

The hybrid architecture effectively fuses local and non-local features.

Pre-training enhances the model's representation capabilities.

Abstract

Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to non-overlapping windows to save computational costs. This means that Transformer-based networks can only use input information from a limited spatial range. Therefore, a novel Hybrid Multi-Axis Aggregation network (HMA) is proposed in this paper to exploit feature potential information better. HMA is constructed by stacking Residual Hybrid Transformer Blocks(RHTB) and Grid Attention Blocks(GAB). On the one side, RHTB combines channel attention and self-attention to enhance non-local feature fusion and produce more attractive visual results. Conversely, GAB is used in cross-domain information interaction to jointly model similar features and obtain a larger perceptual field. For the super-resolution task in the training phase, a novel pre-training method is designed to enhance the model representation capabilities further and validate the proposed model's effectiveness through many experiments. The experimental results show that HMA outperforms the state-of-the-art methods on the benchmark dataset. We provide code and models at https://github.com/korouuuuu/HMA.