Leveraging pretrained RGB denoisers for hyperspectral image restoration 事件

Leveraging pretrained RGB denoisers for hyperspectral image restoration arXiv:2605.24769v1 Announce Type: new Abstract: 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 pr