We are pleased to announce that the following paper, authored by Assistant Professor Yongsong Huang, has been published in the IEEE Transactions on Geoscience and Remote Sensing (TGRS). TGRS is a top-tier journal in the field of remote sensing and geosciences, publishing high-impact research on the theory, concepts, and techniques of sensing the Earth, oceans, atmosphere, and space.

Published Paper

Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi, IRSRMamba: Infrared Image Super-Resolution via Mamba-Based Wavelet Transform Feature Modulation Model, In the IEEE Transactions on Geoscience and Remote Sensing, Vol. 63, 2025

This work addresses the challenge of infrared image super-resolution (IRSR), where images often lack clear textures and details. The paper proposes IRSRMamba, a novel framework that successfully adapts Mamba-based state-space models (SSMs) for high-fidelity IRSR. By integrating a unique wavelet transform feature modulation technique and a semantic consistency loss, IRSRMamba overcomes the spatial fragmentation issues typically associated with Mamba’s blockwise processing, enabling it to restore both fine details and global structural coherence. The model achieves state-of-the-art performance on benchmark datasets.

Congratulations to the authors on this achievement!