TY - JOUR
T1 - Dual-Stage Prior-Driven Diffusion Model for Remote Sensing Spectral Super-Resolution
AU - Li, Zengyi
AU - Gao, Junyu
AU - Yuan, Yuan
N1 - Publisher Copyright:
© 1980-2012 IEEE.
PY - 2025
Y1 - 2025
N2 - Spectral super-resolution (SSR) is a key technology for generating high-spatial-resolution hyperspectral images (HSIs). However, deep learning approaches for SSR, especially generative models like diffusion, often rely heavily on large training datasets. Furthermore, their stochastic generation process can compromise the precise spectral fidelity required in remote sensing. To address this limitation, we propose a dual-stage prior-driven diffusion model (DPDM) for SSR tasks. The DPDM comprises two modules: the prior-driven diffusion module (PDM) and the spectral refinement module (SRM). The PDM replaces the conventional pure noise input with a structured prior, which we term the prior-informed noise (PIN). This PIN is deterministically generated by projecting the input multispectral image (MSI) onto a spectral basis, which is extracted from the spectral response function (SRF). By initializing the reverse process with this information-rich starting point, our model significantly reduces its dependence on large training datasets and inherently enforces spectral consistency. The SRM is subsequently introduced to specifically target and correct residual artifacts and coarse features from the initial stage. Employing a hierarchical multiscale architecture and a single-sample optimization framework, the SRM meticulously restores fine-grained details while suppressing noise in the PDM’s output. By integrating these two modules, the DPDM progressively enhances both spatial and spectral fidelity. Extensive experimental results demonstrate that the DPDM achieves competitive performance in SSR tasks.
AB - Spectral super-resolution (SSR) is a key technology for generating high-spatial-resolution hyperspectral images (HSIs). However, deep learning approaches for SSR, especially generative models like diffusion, often rely heavily on large training datasets. Furthermore, their stochastic generation process can compromise the precise spectral fidelity required in remote sensing. To address this limitation, we propose a dual-stage prior-driven diffusion model (DPDM) for SSR tasks. The DPDM comprises two modules: the prior-driven diffusion module (PDM) and the spectral refinement module (SRM). The PDM replaces the conventional pure noise input with a structured prior, which we term the prior-informed noise (PIN). This PIN is deterministically generated by projecting the input multispectral image (MSI) onto a spectral basis, which is extracted from the spectral response function (SRF). By initializing the reverse process with this information-rich starting point, our model significantly reduces its dependence on large training datasets and inherently enforces spectral consistency. The SRM is subsequently introduced to specifically target and correct residual artifacts and coarse features from the initial stage. Employing a hierarchical multiscale architecture and a single-sample optimization framework, the SRM meticulously restores fine-grained details while suppressing noise in the PDM’s output. By integrating these two modules, the DPDM progressively enhances both spatial and spectral fidelity. Extensive experimental results demonstrate that the DPDM achieves competitive performance in SSR tasks.
KW - Data generation
KW - diffusion model
KW - dual-stage network
KW - hyperspectral image
KW - spectral super-resolution (SSR)
UR - https://www.scopus.com/pages/publications/105013885591
U2 - 10.1109/TGRS.2025.3601119
DO - 10.1109/TGRS.2025.3601119
M3 - 文章
AN - SCOPUS:105013885591
SN - 0196-2892
VL - 63
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
M1 - 5525414
ER -