mlsanityData to 14 Oct 2026

Learning Spectral Diffusion Prior for Hyperspectral Image Reconstruction

arXiv 2507.13769 ↗First posted 18 Jul 2025cs.CV cs.AIcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 10 of its 24 references that are in the map. First posted on arXiv 18 Jul 2025.

Builds on

10 of 24 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023DiffIR: Efficient Diffusion Model for Image Restoration16 Mar
  2. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec

Other references · 8

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
  4. 2018Rank Minimization for Snapshot Compressive Imagingcited by 99
  5. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  6. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  7. 2021Deep Gaussian Scale Mixture Prior for Spectral Compressive Imagingcited by 58
  8. 2023Binarized Spectral Compressive Imagingcited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution
  2. 2025Self-Learning Hyperspectral and Multispectral Image Fusion via Adaptive Residual Guided Subspace Diffusion Model
  3. 2024HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models
  4. 2025Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurements
  5. 2023SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Models
  6. 2026R2H-Diff: Guided Spectral Diffusion Model for RGB-to-Hyperspectral Reconstruction
  7. 2025Diffusion model for gradient preconditioning in hyperspectral imaging inverse problems
  8. 2023Hyperspectral and Multispectral Image Fusion Using the Conditional Denoising Diffusion Probabilistic Model