Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis

TL;DR

This paper introduces a deep generative model-based method to augment spectral libraries in MESMA, enhancing spectral unmixing accuracy by capturing endmember variability more effectively.

Contribution

It proposes a novel library augmentation strategy using deep generative models to improve spectral unmixing performance in MESMA.

Findings

Enhanced spectral unmixing accuracy with augmented libraries.

Effective handling of library mismatch conditions.

Superior performance demonstrated on synthetic and real data.

Abstract

Multiple Endmember Spectral Mixture Analysis (MESMA) is one of the leading approaches to perform spectral unmixing (SU) considering variability of the endmembers (EMs). It represents each EM in the image using libraries of spectral signatures acquired a priori. However, existing spectral libraries are often small and unable to properly capture the variability of each EM in practical scenes, which compromises the performance of MESMA. In this paper, we propose a library augmentation strategy to increase the diversity of existing spectral libraries, thus improving their ability to represent the materials in real images. First, we leverage the power of deep generative models to learn the statistical distribution of the EMs based on the spectral signatures available in the existing libraries. Afterwards, new samples can be drawn from the learned EM distributions and used to augment the spectral libraries, improving the overall quality of the SU process. Experimental results using synthetic and real data attest the superior performance of the proposed method even under library mismatch conditions.