mlsanityData to 14 Oct 2026

Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review

arXiv 2205.09933 ↗First posted 20 May 2022cs.CV eess.IVcited by 13

Not on the map. Why?

Abstract (arXiv)

Hyperspectral unmixing has been an important technique that estimates a set of endmembers and their corresponding abundances from a hyperspectral image (HSI). Nonnegative matrix factorization (NMF) plays an increasingly significant role in solving this problem. In this article, we present a comprehensive survey of the NMF-based methods proposed for hyperspectral unmixing. Taking the NMF model as a baseline, we show how to improve NMF by utilizing the main properties of HSIs (e.g., spectral, spatial, and structural information). We categorize three important development directions including constrained NMF, structured NMF, and generalized NMF. Furthermore, several experiments are conducted to illustrate the effectiveness of associated algorithms. Finally, we conclude the article with possible future directions with the purposes of providing guidelines and inspiration to promote the development of hyperspectral unmixing.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 27 of its 193 references that are in the map. First posted on arXiv 20 May 2022.

Builds on

27 of 193 references.

References · 27

  1. 2017A General and Adaptive Robust Loss Functioncited by 236
  2. 2020Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Reviewcited by 46
  3. 2021Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixingcited by 29
  4. 2015A deep matrix factorization method for learning attribute representationscited by 24
  5. 2017Maximum Volume Inscribed Ellipsoid: A New Simplex-Structured Matrix Factorization Framework via Facet Enumeration and Convex Optimizationcited by 18
  6. 2014Nonlinear hyperspectral unmixing with robust nonnegative matrix factorizationcited by 16
  7. 2017Multilayer tensor factorization with applications to recommender systemscited by 16
  8. 2014Spectral Unmixing via Data-guided Sparsitycited by 14
  9. 2018Hyperspectral Image Unmixing with Endmember Bundles and Group Sparsity Inducing Mixed Normscited by 14
  10. 2015Robust Collaborative Nonnegative Matrix Factorization For Hyperspectral Unmixing (R-CoNMF)cited by 11
  11. 2019Truncated Cauchy Non-negative Matrix Factorizationcited by 11
  12. 2019Algorithms and Comparisons of Non-negative Matrix Factorization with Volume Regularization for Hyperspectral Unmixingcited by 10
15 more
  1. 2014Spectral Unmixing of Hyperspectral Imagery using Multilayer NMFcited by 9
  2. 2020Deep matrix factorizationscited by 9
  3. 2020Superpixel Based Graph Laplacian Regularization for Sparse Hyperspectral Unmixingcited by 7
  4. 2018End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decompositioncited by 6
  5. 2018Low-Rank Tensor Modeling for Hyperspectral Unmixing Accounting for Spectral Variabilitycited by 5
  6. 2020Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Priorcited by 5
  7. 2018A Low-rank Tensor Regularization Strategy for Hyperspectral Unmixingcited by 4
  8. 2018Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorizationcited by 4
  9. 2017Deep Approximately Orthogonal Nonnegative Matrix Factorization for Clusteringcited by 3
  10. 2013Robust Hyperspectral Unmixing with Correntropy based Metriccited by 2
  11. 2015Bi-Objective Nonnegative Matrix Factorization: Linear Versus Kernel-Based Modelscited by 2
  12. 2017Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: a Hyperspectral Unmixing Method Dealing with Intra-class Variabilitycited by 2
  13. 2019Sparsity Constrained Distributed Unmixing of Hyperspectral Datacited by 2
  14. 2019Deep Self-representative Concept Factorization Network for Representation Learningcited by 2
  15. 2019Deep Tensor Factorization for Spatially-Aware Scene Decompositioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 7; 2026: 4.

13 papers.

Sort:

By area:

  1. 2025Adaptive Multi-Order Graph Regularized NMF with Dual Sparsity for Hyperspectral Unmixingcited by 3
  2. 2023Bidirectional recurrent imputation and abundance estimation of LULC classes with MODIS multispectral time series and geo-topographic and climatic datacited by 0
  3. 2024Learning nonnegative matrix factorizations from compressed datacited by 0
  4. 2025Neural Network for Blind Unmixing: a novel MatrixConv Unmixing (MCU) Approachcited by 0
  5. 2025Hyperspectral Image Generation with Unmixing Guided Diffusion Modelcited by 0
  6. 2025Leveraging Convolutional and Graph Networks for an Unsupervised Remote Sensing Labelling Toolcited by 0
  7. 2025Phase-Locked SNR Band Selection for Weak Mineral Signal Detection in Hyperspectral Imagerycited by 0
  8. 2025Sparsity and Total Variation Constrained Multilayer Linear Unmixing for Hyperspectral Imagerycited by 0
  9. 2025Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixingcited by 0
  10. 2026WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusioncited by 0
  11. 2026Polyhedral Unmixing: Bridging Semantic Segmentation with Hyperspectral Unmixing via Polyhedral-Cone Partitioningcited by 0
  12. 2026A Deep Equilibrium Network for Hyperspectral Unmixingcited by 0
1 more
  1. 2026Hyperspectral Unmixing Hierarchiescited by 0