FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization

ArXi:2605.15880v1 Announce Type: cross Thermal infrared imaging is robust to illumination variations and smoke interference, making it important for all-weather perception. However, the lack of natural color and fine texture limits target recognition, human visual interpretation, and the transfer of visible-light models. Existing infrared colorization methods mainly rely on single-band images, where insufficient spectral cues may lead to structural distortion and semantic confusion.