Learning Spectral Diffusion Prior for Hyperspectral Image Reconstruction
This work addresses the challenge of accurately reconstructing hyperspectral images for applications in remote sensing or imaging, representing an incremental advancement in deep learning-based methods.
The paper tackled the problem of hyperspectral image reconstruction by proposing a Spectral Diffusion Prior to capture high-frequency details, resulting in a performance improvement of about 0.5 dB over existing methods.
Hyperspectral image (HSI) reconstruction aims to recover 3D HSI from its degraded 2D measurements. Recently great progress has been made in deep learning-based methods, however, these methods often struggle to accurately capture high-frequency details of the HSI. To address this issue, this paper proposes a Spectral Diffusion Prior (SDP) that is implicitly learned from hyperspectral images using a diffusion model. Leveraging the powerful ability of the diffusion model to reconstruct details, this learned prior can significantly improve the performance when injected into the HSI model. To further improve the effectiveness of the learned prior, we also propose the Spectral Prior Injector Module (SPIM) to dynamically guide the model to recover the HSI details. We evaluate our method on two representative HSI methods: MST and BISRNet. Experimental results show that our method outperforms existing networks by about 0.5 dB, effectively improving the performance of HSI reconstruction.