Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks

TL;DR

This paper proposes a lightweight multi-scale attention network for image super-resolution that effectively balances high-quality reconstruction with low model complexity, outperforming many existing methods.

Contribution

Introduction of the Multi-scale Spatial Adaptive Attention Network (MSAAN) with novel modules for improved feature fusion and local detail enhancement in super-resolution tasks.

Findings

Achieves superior PSNR and SSIM on standard benchmarks.

Maintains lower parameters and computational costs than state-of-the-art.

Reconstructs sharper edges and more realistic textures.

Abstract

This paper introduces a lightweight image super-resolution (SR) network, termed the Multi-scale Spatial Adaptive Attention Network (MSAAN), to address the common dilemma between high reconstruction fidelity and low model complexity in existing SR methods. The core of our approach is a novel Multi-scale Spatial Adaptive Attention Module (MSAA), designed to jointly model fine-grained local details and long-range contextual dependencies. The MSAA comprises two synergistic components: a Global Feature Modulation Module (GFM) that learns coherent texture structures through differential feature extraction, and a Multi-scale Feature Aggregation Module (MFA) that adaptively fuses features from local to global scales using pyramidal processing. To further enhance the network's capability, we propose a Local Enhancement Block (LEB) to strengthen local geometric perception and a Feature Interactive Gated Feed-Forward Module (FIGFF) to improve nonlinear representation while reducing channel redundancy. Extensive experiments on standard benchmarks (Set5, Set14, B100, Urban100, Manga109) across $\times2$, $\times3$, and $\times4$ scaling factors demonstrate that both our lightweight (MSAAN-light) and standard (MSAAN) versions achieve superior or competitive performance in terms of PSNR and SSIM, while maintaining significantly lower parameters and computational costs than state-of-the-art methods. Ablation studies validate the contribution of each component, and visual results show that MSAAN reconstructs sharper edges and more realistic textures.