TY - GEN
T1 - R2H-CCD
T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
AU - Zhang, Lei
AU - Luo, Xiaoyan
AU - Li, Sen
AU - Shi, Xiaofeng
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Hyperspectral imaging can capture detailed spectra of materials, but due to imaging conditions and equipment limitations, the cost of hyperspectral data collection is extremely high. Leveraging low-priced and easy-obtainable RGB images to generate hyperspectral images (HSIs) has gradually become a trend. Benefiting from the advantages of the denoising diffusion probability model (DDPM) in natural image super-resolution tasks, we consider the structural characteristics of HSI to design a novel spectral super-resolution algorithm, named R2H-CCD, which is a hyperspectral imagery generation method from RGB images based on conditional cascade diffusion probabilistic models. More specifically, the algorithm takes RGB image as conditional input and synthesise corresponding HSI from pure noise through a stochastic iterative denoising process. In addition, to obtain high-fidelity HSIs, it adopts U-Net structure to iteratively refine the generated images in an end-to-end training manner. The experiments on HFD100 dataset show the effectiveness and superiority of the proposed method.
AB - Hyperspectral imaging can capture detailed spectra of materials, but due to imaging conditions and equipment limitations, the cost of hyperspectral data collection is extremely high. Leveraging low-priced and easy-obtainable RGB images to generate hyperspectral images (HSIs) has gradually become a trend. Benefiting from the advantages of the denoising diffusion probability model (DDPM) in natural image super-resolution tasks, we consider the structural characteristics of HSI to design a novel spectral super-resolution algorithm, named R2H-CCD, which is a hyperspectral imagery generation method from RGB images based on conditional cascade diffusion probabilistic models. More specifically, the algorithm takes RGB image as conditional input and synthesise corresponding HSI from pure noise through a stochastic iterative denoising process. In addition, to obtain high-fidelity HSIs, it adopts U-Net structure to iteratively refine the generated images in an end-to-end training manner. The experiments on HFD100 dataset show the effectiveness and superiority of the proposed method.
KW - Hyperspectral image
KW - denoising diffusion probability model
KW - image generation
KW - spectral super-resolution
UR - https://www.scopus.com/pages/publications/85178332140
U2 - 10.1109/IGARSS52108.2023.10281589
DO - 10.1109/IGARSS52108.2023.10281589
M3 - 会议稿件
AN - SCOPUS:85178332140
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 7392
EP - 7395
BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 16 July 2023 through 21 July 2023
ER -