Deep Diffusion Models and Unsupervised Hyperspectral Unmixing for Realistic Abundance Map Synthesis

TL;DR

This paper introduces an unsupervised deep learning framework combining hyperspectral unmixing and diffusion models to generate realistic synthetic abundance maps, aiding data augmentation and analysis in hyperspectral imaging.

Contribution

It presents a novel unsupervised method integrating blind unmixing with diffusion models for realistic hyperspectral abundance map synthesis.

Findings

Successfully generates realistic abundance maps from real hyperspectral data.

Enhances diversity and realism of synthetic hyperspectral data.

Validated on PRISMA satellite imagery with promising results.

Abstract

This paper presents a novel methodology for generating realistic abundance maps from hyperspectral imagery using an unsupervised, deep-learning-driven approach. Our framework integrates blind linear hyperspectral unmixing with state-of-the-art diffusion models to enhance the realism and diversity of synthetic abundance maps. First, we apply blind unmixing to extract endmembers and abundance maps directly from raw hyperspectral data. These abundance maps then serve as inputs to a diffusion model, which acts as a generative engine to synthesize highly realistic spatial distributions. Diffusion models have recently revolutionized image synthesis by offering superior performance, flexibility, and stability, making them well-suited for high-dimensional spectral data. By leveraging this combination of physically interpretable unmixing and deep generative modeling, our approach enables the simulation of hyperspectral sensor outputs under diverse imaging conditions--critical for data augmentation, algorithm benchmarking, and model evaluation in hyperspectral analysis. Notably, our method is entirely unsupervised, ensuring adaptability to different datasets without the need for labeled training data. We validate our approach using real hyperspectral imagery from the PRISMA space mission for Earth observation, demonstrating its effectiveness in producing realistic synthetic abundance maps that capture the spatial and spectral characteristics of natural scenes.