IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model

TL;DR

This paper introduces IRSRMamba, a novel infrared image super-resolution framework that combines wavelet transform feature modulation with Mamba-based state-space models to improve detail preservation, structural coherence, and reduce artifacts.

Contribution

It presents a new IR super-resolution model integrating wavelet-based feature modulation and Mamba SSMs, enhancing global-local feature fusion and image quality.

Findings

Outperforms state-of-the-art methods in PSNR and SSIM

Achieves better perceptual quality and structural coherence

Reduces block-induced artifacts in IR image reconstruction

Abstract

Infrared image super-resolution demands long-range dependency modeling and multi-scale feature extraction to address challenges such as homogeneous backgrounds, weak edges, and sparse textures. While Mamba-based state-space models (SSMs) excel in global dependency modeling with linear complexity, their block-wise processing disrupts spatial consistency, limiting their effectiveness for IR image reconstruction. We propose IRSRMamba, a novel framework integrating wavelet transform feature modulation for multi-scale adaptation and an SSMs-based semantic consistency loss to restore fragmented contextual information. This design enhances global-local feature fusion, structural coherence, and fine-detail preservation while mitigating block-induced artifacts. Experiments on benchmark datasets demonstrate that IRSRMamba outperforms state-of-the-art methods in PSNR, SSIM, and perceptual quality. This work establishes Mamba-based architectures as a promising direction for high-fidelity IR image enhancement. Code are available at https://github.com/yongsongH/IRSRMamba.