Official PyTorch implementation of the paper IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model.
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.
Please check here.
- Python 3.8, PyTorch >= 1.11
- BasicSR 1.4.2
- Platforms: Ubuntu 18.04, cuda-11
Clone the repo
git clone https://github.com/yongsongH/IRSRMamba.git
Install dependent packages
cd IRSRMamba
pip install -r install.txt
Install BasicSR
python setup.py develop
You can also refer to this INSTALL.md for installation
Please check this page.
Pre-trained models can be downloaded from this link.
please check the log file for more information about the settings.
Run
python basicsr/test.py -opt options/test/test_IRSRMamba_x4.yml
python basicsr/test.py -opt options/test/test_IRSRMamba_x2.yml
If you meet any problems, please describe them and contact me.
Impolite or anonymous emails are not welcome. There may be some difficulties for me to respond to the email without self-introduce. Thank you for understanding.
This work is under peer review. The updated manuscript and training dataset will be released after the paper is accepted.