{"ID":2853513,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16664","arxiv_id":"2510.16664","title":"HYDRA: HYbrid knowledge Distillation and spectral Reconstruction Algorithm for high channel hyperspectral camera applications","abstract":"Hyperspectral images (HSI) promise to support a range of new applications in computer vision. Recent research has explored the feasibility of generalizable Spectral Reconstruction (SR), the problem of recovering a HSI from a natural three-channel color image in unseen scenarios. However, previous Multi-Scale Attention (MSA) works have only demonstrated sufficient generalizable results for very sparse spectra, while modern HSI sensors contain hundreds of channels. This paper introduces a novel approach to spectral reconstruction via our HYbrid knowledge Distillation and spectral Reconstruction Architecture (HYDRA). Using a Teacher model that encapsulates latent hyperspectral image data and a Student model that learns mappings from natural images to the Teacher's encoded domain, alongside a novel training method, we achieve high-quality spectral reconstruction. This addresses key limitations of prior SR models, providing SOTA performance across all metrics, including an 18\\% boost in accuracy, and faster inference times than current SOTA models at various channel depths.","short_abstract":"Hyperspectral images (HSI) promise to support a range of new applications in computer vision. Recent research has explored the feasibility of generalizable Spectral Reconstruction (SR), the problem of recovering a HSI from a natural three-channel color image in unseen scenarios. However, previous Multi-Scale Attention...","url_abs":"https://arxiv.org/abs/2510.16664","url_pdf":"https://arxiv.org/pdf/2510.16664v1","authors":"[\"Christopher Thirgood\",\"Oscar Mendez\",\"Erin Ling\",\"Jon Storey\",\"Simon Hadfield\"]","published":"2025-10-18T23:29:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}