IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model
This work addresses the problem of high-fidelity infrared image enhancement for applications like surveillance or medical imaging, representing an incremental improvement by adapting Mamba-based models with novel components for this domain.
The paper tackles infrared image super-resolution by proposing IRSRMamba, a framework that integrates wavelet transform feature modulation and an SSMs-based semantic consistency loss to enhance global-local feature fusion and structural coherence, achieving state-of-the-art performance in PSNR, SSIM, and perceptual quality on benchmark datasets.
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.