Diffusion model with disentangled modulations for sharpening multispectral and hyperspectral images

Open Webpage

Zihan Cao, Shiqi Cao, Liang-Jian Deng, Xiao Wu, Junming Hou, Gemine Vivone

Published: 2024, Last Modified: 04 Nov 2025Inf. Fusion 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A novel diffusion model with disentangled modulations is proposed for image fusion.•Two modulation modules disentangle style and frequency parts from diverse domains.•Our method reaches new SOTA performances on different fusion benchmarks.