Hyperspectral Image Generation with Unmixing Guided Diffusion Model

TL;DR

This paper introduces a novel diffusion-based framework guided by hyperspectral unmixing for generating high-quality, diverse hyperspectral images while respecting physical constraints, addressing limitations of existing methods.

Contribution

The paper presents a hyperspectral unmixing-guided diffusion model that enhances diversity and physical accuracy in hyperspectral image synthesis, a significant advancement over prior approaches.

Findings

Produces hyperspectral images with high quality and diversity

Enforces physical constraints like non-negativity and sum-to-one

Outperforms existing methods on conventional and proposed metrics

Abstract

We address hyperspectral image (HSI) synthesis, a problem that has garnered growing interest yet remains constrained by the conditional generative paradigms that limit sample diversity. While diffusion models have emerged as a state-of-the-art solution for high-fidelity image generation, their direct extension from RGB to hyperspectral domains is challenged by the high spectral dimensionality and strict physical constraints inherent to HSIs. To overcome the challenges, we introduce a diffusion framework explicitly guided by hyperspectral unmixing. The approach integrates two collaborative components: (i) an unmixing autoencoder that projects generation from the image domain into a low-dimensional abundance manifold, thereby reducing computational burden while maintaining spectral fidelity; and (ii) an abundance diffusion process that enforces non-negativity and sum-to-one constraints, ensuring physical consistency of the synthesized data. We further propose two evaluation metrics tailored to hyperspectral characteristics. Comprehensive experiments, assessed with both conventional measures and the proposed metrics, demonstrate that our method produces HSIs with both high quality and diversity, advancing the state of the art in hyperspectral data generation.