A three-stage plug-and-play framework uses proxy HSIs, blur-robust diffusion synthesis, and spectral transfer to augment training data for target-adaptive hyperspectral restoration.
Hir-diff: Unsupervised hyperspectral image restoration via improved diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
TGPNet unifies denoising, cloud removal, shadow removal, deblurring, and SAR despeckling into one model via task-guided prompting and reports state-of-the-art results on a new multi-modal benchmark.
citing papers explorer
-
HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation
A three-stage plug-and-play framework uses proxy HSIs, blur-robust diffusion synthesis, and spectral transfer to augment training data for target-adaptive hyperspectral restoration.