Leveraging pretrained RGB denoisers for hyperspectral image restoration
For hyperspectral imaging practitioners, this method reduces the need for large hyperspectral training datasets by leveraging RGB priors.
The paper proposes a lightweight adapter that repurposes frozen pretrained RGB denoisers for hyperspectral image restoration, achieving consistent improvements over hyperspectral-specific baselines across denoising, deblurring, and super-resolution tasks.
Hyperspectral image restoration faces several challenges, including limited training data, strong sensor specificity, and high spectral dimensionality. These limitations hinder the learning of robust hyperspectral priors, motivating the reuse of priors learned from large-scale RGB data. In this work, we propose a minimally trained, lightweight adapter that repurposes frozen pretrained RGB denoisers for hyperspectral restoration through a projection mapping. The method denoises low-dimensional spectral projections and reconstructs the hyperspectral cube through constrained linear aggregation, while preserving plug-and-play compatibility and the stability properties of the underlying RGB denoiser. Experiments on denoising, deblurring, and super-resolution across multiple datasets demonstrate consistent improvements over hyperspectral-specific baselines, showing the strong transferability of large-scale RGB priors.