{"ID":2894641,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09885","arxiv_id":"2507.09885","title":"MCGA: Mixture of Codebooks Hyperspectral Reconstruction via Grayscale-Aware Attention","abstract":"Reconstructing hyperspectral images (HSIs) from RGB inputs provides a cost-effective alternative to hyperspectral cameras, but reconstructing high-dimensional spectra from three channels is inherently ill-posed. Existing methods typically directly regress RGB-to-HSI mappings using large attention networks, which are computationally expensive and handle ill-posedness only implicitly. We propose MCGA, a Mixture-of-Codebooks with Grayscale-aware Attention framework that explicitly addresses these challenges using spectral priors and photometric consistency. MCGA first learns transferable spectral priors via a mixture-of-codebooks (MoC) from heterogeneous HSI datasets, then aligns RGB features with these priors through grayscale-aware photometric attention (GANet). Efficiency and robustness are further improved via top-K attention design and test-time adaptation (TTA). Experiments on multiple real-world benchmarks demonstrate the state-of-the-art accuracy, strong cross-dataset generalization, and 4-5x faster inference. Codes will be available once acceptance at https://github.com/Fibonaccirabbit/MCGA.","short_abstract":"Reconstructing hyperspectral images (HSIs) from RGB inputs provides a cost-effective alternative to hyperspectral cameras, but reconstructing high-dimensional spectra from three channels is inherently ill-posed. Existing methods typically directly regress RGB-to-HSI mappings using large attention networks, which are co...","url_abs":"https://arxiv.org/abs/2507.09885","url_pdf":"https://arxiv.org/pdf/2507.09885v3","authors":"[\"Zhanjiang Yang\",\"Lijun Sun\",\"Jiawei Dong\",\"Xiaoxin An\",\"Yang Liu\",\"Meng Li\"]","published":"2025-07-14T03:46:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":612118,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2894641,"paper_url":"https://arxiv.org/abs/2507.09885","paper_title":"MCGA: Mixture of Codebooks Hyperspectral Reconstruction via Grayscale-Aware Attention","repo_url":"https://github.com/Fibonaccirabbit/MCGA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}