Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network
This work addresses the challenge of enhancing hyperspectral images for applications like remote sensing, but it is incremental as it adapts existing diffusion models with a new encoding framework.
The authors tackled the problem of hyperspectral image super-resolution by introducing a Group-Autoencoder framework combined with a diffusion model to overcome training and inference challenges, achieving superior visual and metric results compared to state-of-the-art methods on natural and remote sensing datasets.
Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features. The direct application of diffusion models to HSI SR is hampered by challenges such as difficulties in model convergence and protracted inference time. In this work, we introduce a novel Group-Autoencoder (GAE) framework that synergistically combines with the diffusion model to construct a highly effective HSI SR model (DMGASR). Our proposed GAE framework encodes high-dimensional HSI data into low-dimensional latent space where the diffusion model works, thereby alleviating the difficulty of training the diffusion model while maintaining band correlation and considerably reducing inference time. Experimental results on both natural and remote sensing hyperspectral datasets demonstrate that the proposed method is superior to other state-of-the-art methods both visually and metrically.