Deep Generative Model for Spatial-spectral Unmixing with Multiple Endmember Priors

Shuaikai Shi, Lijun Zhang, Yoann Altmann, Jie Chen

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)


Spectral unmixing is an effective tool to mine information at the subpixel level from complex hyperspectral images. To consider the spatially correlated materials distributions in the scene, many algorithms unmix the data in a spatial-spectral fashion; however, existing models are usually unable to model spectral variability simultaneously. In this article, we present a variational autoencoder-based deep generative model for spatial-spectral unmixing (DGMSSU) with endmember variability, by linking the generated endmembers to the probability distributions of endmember bundles extracted from the hyperspectral imagery via discriminators. Besides the convolutional autoencoder-like architecture that can only model the spatial information within the regular patch inputs, DGMSSU is able to alternatively choose graph convolutional networks or self-attention mechanism modules to handle the irregular but more flexible data - superpixel. Experimental results on a simulated dataset, as well as two well-known real hyperspectral images, show the superiority of our proposed approach in comparison with other state-of-the-art spatial-spectral unmixing methods. Compared to the conventional unmixing methods that consider the endmember variability, our proposed model generates more accurate endmembers on each subimage by the adversarial training process. The codes of this work will be available at for the sake of reproducibility.

Original languageEnglish
Article number5527214
JournalIEEE Transactions on Geoscience and Remote Sensing
Publication statusPublished - 18 Apr 2022


  • Deep neural network
  • endmember variability
  • graph convolution
  • self-attention
  • spatial-spectral model
  • spectral unmixing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • General Earth and Planetary Sciences


Dive into the research topics of 'Deep Generative Model for Spatial-spectral Unmixing with Multiple Endmember Priors'. Together they form a unique fingerprint.

Cite this