HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution

TL;DR

This paper introduces HAAT, a novel transformer-based model for image super-resolution that combines dense residual blocks with hybrid attention mechanisms to improve feature utilization and outperform existing methods.

Contribution

The paper proposes HAAT, integrating SDRCB and HGAB to enhance receptive fields and attention mechanisms, advancing super-resolution performance.

Findings

HAAT outperforms state-of-the-art methods on benchmark datasets.

Enhanced feature fusion through hybrid attention improves image quality.

Receptive field expansion leads to better detail recovery.

Abstract

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to non overlapping windows to cut costs and ignore the useful information that exists across channels. To address this issue, this paper introduces a novel model, the Hybrid Attention Aggregation Transformer (HAAT), designed to better leverage feature information. HAAT is constructed by integrating Swin-Dense-Residual-Connected Blocks (SDRCB) with Hybrid Grid Attention Blocks (HGAB). SDRCB expands the receptive field while maintaining a streamlined architecture, resulting in enhanced performance. HGAB incorporates channel attention, sparse attention, and window attention to improve nonlocal feature fusion and achieve more visually compelling results. Experimental evaluations demonstrate that HAAT surpasses state-of-the-art methods on benchmark datasets. Keywords: Image super-resolution, Computer vision, Attention mechanism, Transformer