USP-Mamba enhances hyperspectral image super-resolution with spectral and structural prompting

Researchers have developed USP-Mamba, a novel framework for hyperspectral image super-resolution that enhances Mamba-based models. This new approach addresses limitations in existing models by incorporating unmixing-derived spectral priors and image-dependent structural prompts to better capture material composition and local details. Extensive experiments show that USP-Mamba consistently outperforms current representative methods on various datasets. AI

IMPACT Introduces a novel Mamba-based framework that improves hyperspectral image reconstruction by incorporating spectral and structural priors.

RANK_REASON This is a research paper detailing a new method for hyperspectral image super-resolution. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• Hilbert
• Hugging Face
• Mamba
• Semantic-Guided Neighboring
• USP-Mamba

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →