MCGA: Mixture of Codebooks Hyperspectral Reconstruction via Grayscale-Aware Attention
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914213336711168 |
|---|---|
| author | Yang, Zhanjiang Sun, Lijun Dong, Jiawei An, Xiaoxin Liu, Yang Li, Meng |
| author_facet | Yang, Zhanjiang Sun, Lijun Dong, Jiawei An, Xiaoxin Liu, Yang Li, Meng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09885 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MCGA: Mixture of Codebooks Hyperspectral Reconstruction via Grayscale-Aware Attention Yang, Zhanjiang Sun, Lijun Dong, Jiawei An, Xiaoxin Liu, Yang Li, Meng Computer Vision and Pattern Recognition 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. |
| title | MCGA: Mixture of Codebooks Hyperspectral Reconstruction via Grayscale-Aware Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.09885 |