Kronecker-Basis-Representation Based Tensor Sparsity and Its Applications to Tensor Recovery

As a promising way for analyzing data, sparse modeling has achieved great success throughout science and engineering. It is well known that the sparsity/low-rank of a vector/matrix can be rationally measured by nonzero-entries-number ($l_0$ norm)/nonzero- singular-values-number (rank), respectively. However, data from real applications are often generated by the interaction of multiple factors, which obviously cannot be sufficiently represented by a vector/matrix, while a high order tensor is expected to provide more faithful representation to deliver the intrinsic structure underlying such data ensembles. Unlike the vector/matrix case, constructing a rational high order sparsity measure for tensor is a relatively harder task. To this aim, in this paper we propose a measure for tensor sparsity, called Kronecker-basis-representation based tensor sparsity measure (KBR briefly), which encodes both sparsity insights delivered by Tucker and CANDECOMP/PARAFAC (CP) low-rank decompositions for a general tensor. Then we study the KBR regularization minimization (KBRM) problem, and design an effective ADMM algorithm for solving it, where each involved parameter can be updated with closed-form equations. Such an efficient solver makes it possible to extend KBR to various tasks like tensor completion and tensor robust principal component analysis. A series of experiments, including multispectral image (MSI) denoising, MSI completion and background subtraction, substantiate the superiority of the proposed methods beyond state-of-the-arts.

• Publication year

  2018

• Venue

  IEEE Transactions on Pattern Analysis and Machine Intelligence

• Publication date

  2018-08-01

• Fields of study

  Mathematics, Computer Science, Engineering, Medicine

• Identifiers
  DOI 10.1109/TPAMI.2017.2734888PMID 28783623
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Low rank tensor recovery via iterative hard thresholding

  2016cited by this paper
• Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization

  2016influential reference
• Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization

  2016cited by this paper
• Total-Variation-Regularized Low-Rank Matrix Factorization for Hyperspectral Image Restoration

  2016cited by this paper
• Folded-concave penalization approaches to tensor completion

  2015cited by this paper
• A Novel Tensor Robust PCA Approach for Background Subtraction from Compressive Measurements

  2015influential reference
• Total Variation Regularized Tensor RPCA for Background Subtraction From Compressive Measurements

  2015cited by this paper
• Weighted Nuclear Norm Minimization with Application to Image Denoising

  2014cited by this paper
• Hyperspectral Image Restoration Using Low-Rank Matrix Recovery

  2014cited by this paper
• Low-Rank Tensor Completion with Spatio-Temporal Consistency

  2014cited by this paper
• Robust Principal Component Analysis with Complex Noise

  2014cited by this paper
• Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising

  2014cited by this paper
• Generalized Singular Value Thresholding

  2014cited by this paper
• Novel Methods for Multilinear Data Completion and De-noising Based on Tensor-SVD

  2014influential reference
• Fast and Accurate Matrix Completion via Truncated Nuclear Norm Regularization

  2013cited by this paper
• A New Convex Relaxation for Tensor Completion

  2013cited by this paper
• Robust Low-Rank Tensor Recovery: Models and Algorithms

  2013cited by this paper
• Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction

  2013cited by this paper
• Intersecting singularities for multi-structured estimation

  2013cited by this paper
• A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems

  2013cited by this paper
• Parallel matrix factorization for low-rank tensor completion

  2013cited by this paper
• Robust Matrix Factorization with Unknown Noise

  2013cited by this paper
• Deblurring and Sparse Unmixing for Hyperspectral Images

  2013cited by this paper
• Nonlocal Image Restoration With Bilateral Variance Estimation: A Low-Rank Approach

  2013cited by this paper
• Estimation of Simultaneously Sparse and Low Rank Matrices

  2012cited by this paper
• The inpainting of hyperspectral images: a survey and adaptation to hyperspectral data

  2012cited by this paper
• Hyperspectral image compressed sensing via low-rank and joint-sparse matrix recovery

  2012cited by this paper
• Joint trace/TV norm minimization: A new efficient approach for spectral compressive imaging

  2012influential reference
• Nonlocal transform-domain denoising of volumetric data with groupwise adaptive variance estimation

  2012cited by this paper
• Denoising of Hyperspectral Images Using the PARAFAC Model and Statistical Performance Analysis

  2012cited by this paper
• Bayesian Robust Principal Component Analysis

  2011cited by this paper
• Tensor completion and low-n-rank tensor recovery via convex optimization

  2011cited by this paper
• High-resolution hyperspectral imaging via matrix factorization

  2011cited by this paper
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers

  2011cited by this paper
• Sparse channel estimation with lp-norm and reweighted l1-norm penalized least mean squares

  2011cited by this paper
• Sparse Bayesian Methods for Low-Rank Matrix Estimation

  2011cited by this paper
• FSIM: A Feature Similarity Index for Image Quality Assessment

  2011cited by this paper
• Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation

  2011cited by this paper
• Tensor completion for on-board compression of hyperspectral images

  2010cited by this paper
• Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L1 norm

  2010cited by this paper
• The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices

  2010influential reference
• Generalized Assorted Pixel Camera: Postcapture Control of Resolution, Dynamic Range, and Spectrum

  2010cited by this paper
• Comparative study of background subtraction algorithms

  2010cited by this paper
• Adaptive non‐local means denoising of MR images with spatially varying noise levels

  2010cited by this paper
• Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix

  2009cited by this paper
• Robust principal component analysis?

  2009cited by this paper
• Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization

  2009cited by this paper
• Tensor Decompositions and Applications

  2009cited by this paper
• Tensor Completion for Estimating Missing Values in Visual Data

  2009cited by this paper
• A Retrospective

  2009cited by this paper
• Matrix Completion With Noise

  2009cited by this paper
• Recovering Sparse Signals Using Sparse Measurement Matrices in Compressed DNA Microarrays

  2008cited by this paper
• Denoising and Dimensionality Reduction Using Multilinear Tools for Hyperspectral Images

  2008cited by this paper
• Exact Matrix Completion via Convex Optimization

  2008cited by this paper
• Algorithms for Sparse Nonnegative Tucker Decompositions

  2008cited by this paper
• Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering

  2007cited by this paper
• Enhancing Sparsity by Reweighted ℓ1 Minimization

  2007cited by this paper
• Video Inpainting Under Constrained Camera Motion

  2007cited by this paper
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

  2006cited by this paper
• Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries

  2006cited by this paper
• Robust L/sub 1/ norm factorization in the presence of outliers and missing data by alternative convex programming

  2005cited by this paper
• K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation

  2005cited by this paper
• Damped Newton algorithms for matrix factorization with missing data

  2005cited by this paper
• Higher-order Web link analysis using multilinear algebra

  2005cited by this paper
• Statistical modeling of complex backgrounds for foreground object detection

  2004cited by this paper
• On Photometric Issues in 3D Visual Recognition from a Single 2D Image

  2004cited by this paper
• Image quality assessment: from error visibility to structural similarity

  2004cited by this paper
• Weighted Low-Rank Approximations

  2003cited by this paper
• A Framework for Robust Subspace Learning

  2003cited by this paper
• Data Fusion. Definitions and Architectures - Fusion of Images of Different Spatial Resolutions

  2002cited by this paper
• A Multilinear Singular Value Decomposition

  2000cited by this paper
• 3D image reconstruction for a Compton SPECT camera model

  1999cited by this paper
• MICROARRAY EXPERIMENTS : APPLICATION TO SPORULATION TIME SERIES

  1999cited by this paper
• De-noising by soft-thresholding

  1995cited by this paper
• A trace inequality of John von Neumann

  1975cited by this paper
• Some mathematical notes on three-mode factor analysis

  1966cited by this paper

• Tensor Wheel Completion With Low-Rank Factor Prior and Adaptive Graph Regularizer for Hyperspectral Image Recovery

  2026cites this paper
• Multi-channel audio restoration algorithm based on tensor correlated total variation

  2026cites this paper
• Robust Tensor Completion via Tensor Wheel Decomposition with Difference Factors Regularization for Hyperspectral Image Restoration

  2026cites this paper
• Unsupervised Hyperspectral Image Denoising via Spectral Learning Preference of Neural Networks

  2026cites this paper
• TuckerAPP: A novel spatiotemporal Tucker decomposition approach for traffic imputation

  2026cites this paper
• Double Nonconvex Tensor Robust Kernel Principal Component Analysis and Its Visual Applications

  2026cites this paper
• RL-Driven Distributed On-Orbit Sparse Coding for Mobile Space Situational Awareness

  2026cites this paper
• Enhancing Tucker Tensor Completion via Laplace-Like Nonconvex Surrogates and Structural Regularization

  2026cites this paper
• Intelligent recovery of low-rank sparse tensor for noisy hydroacoustic with use of nonconvex regularization

  2026cites this paper
• Neural Operator-Grounded Continuous Tensor Function Representation and Its Applications

  2026cites this paper
• Effective Non-Gaussian Noise Removal of 3D Radio Maps Through Correntropy-Based Nonlocal Tensor Ring Decomposition

  2026cites this paper
• TenExp: Mixture-of-Experts-Based Tensor Decomposition Structure Search Framework

  2026cites this paper
• Foreground detection through feature fusion convolutional neural networks: enhancing robustness against complex backgrounds

  2025cites this paper
• Bayesian high-order tensor factorization for learning the hidden low-rank structure

  2025cites this paper
• Boosting RPCA by Prior Subspace

  2025influential citation
• Outlier-aware Tensor Robust Principal Component Analysis with Self-guided Data Augmentation

  2025cites this paper
• Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations

  2025cites this paper
• Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising.

  2025cites this paper
• Robust Low‐Rank Tensor Recovery Using a Self‐Adaptive Learnable Weighted Tensor Total Variation Method

  2025cites this paper
• Image Denoising Algorithm Based on Multivariate Gaussian Mixture Model

  2025cites this paper
• SS3L: Self-Supervised Spectral–Spatial Subspace Learning for Hyperspectral Image Denoising

  2025cites this paper
• Accelerating Large-Scale Regularized High-Order Tensor Recovery

  2025cites this paper
• A unified network for noise hyperspectral anomaly detection based on autoencoder-transformer architecture

  2025cites this paper
• Pair-mode tensor wheel decomposition with randomized block Krylov iteration

  2025cites this paper
• Parameterized Low-Rank Regularizer for High-dimensional Visual Data

  2025cites this paper
• Under-Sampled High-Dimensional Data Recovery via Symbiotic Multi-Prior Tensor Reconstruction

  2025influential citation
• Denoising of 3D magnetic resonance images via edge-enhanced low-rank tensor decomposition.

  2025cites this paper
• Manifold regularized tensor completion with low-rank Tucker factor prior for hyperspectral image recovery

  2025cites this paper
• Beyond Motion Cues and Structural Sparsity: Revisiting Small Moving Target Detection

  2025cites this paper
• Multi-Priors Tensor Completion for Highly Under-sampled Magnetic Flux Leakage Signal Reconstruction

  2025cites this paper
• EGD-Net: Eigenimage Guided Diffusion Network for Hyperspectral Mixed Noise Removal

  2025cites this paper
• Tensor network decomposition for data recovery: Recent advancements and future prospects

  2025cites this paper
• Beyond Low-rankness: Guaranteed Matrix Recovery via Modified Nuclear Norm

  2025influential citation
• Low-Rank Tensor Recovery Based on Nonconvex Geman Norm and Total Variation

  2025cites this paper
• Efficient and compact tensor wheel decomposition for tensor completion

  2025cites this paper
• $\mathrm{D}^{3}$T: Deep Denoising Dictionary Tensor for Hyperspectral Anomaly Detection

  2025cites this paper
• VolFormer: Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond

  2025cites this paper
• Transformed sparsity-boosted low-rank model for image inpainting with non-convex γ-norm regularization and non-local prior

  2025cites this paper
• Remote Sensing Image Restoration Based on Image Tensor and Noise Modeling

  2025cites this paper
• Nonconvex tensor logarithmic function-based tensor robust principal component analysis for foreground detection

  2025cites this paper
• Hyperspectral Image Denoising via Low-Rank Tucker Decomposition with Subspace Implicit Neural Representation

  2025cites this paper
• HyDeFuse: provably convergent denoiser-driven hyperspectral fusion

  2025cites this paper
• Image denoising via double-weighted correlated total variation regularization

  2025cites this paper
• Exact tensor gradient decomposition: A coupled low-rank and sparse framework for guaranteed recovery

  2025cites this paper
• Hypergraph Regularized and Low-rank enhanced Tucker Decomposition for Image Restoration

  2025cites this paper
• Tensor Multi-Subspace Representation for Remote Sensing Image Mixed Noise Removal

  2025cites this paper
• Fast Reconstruction Method for Block Compressed Sensing Based on Semi-Tensor Product-BCS

  2025cites this paper
• Guided Feature Fusion: Zero-Shot Framework for Hyperspectral Image Denoising

  2025cites this paper
• Manifold Low Rank and Sparse Tensor Method for High-Resolution Radar Imaging

  2025cites this paper
• DELTA: Deep Low-Rank Tensor Representation for Multi-Dimensional Data Recovery

  2025cites this paper
• MSFA Image Denoising Using Physics-Based Noise Model and Noise-Decoupled Network

  2025cites this paper
• Constructing 4D Radio Map in LEO Satellite Networks with Limited Samples

  2025influential citation
• LRTuckerRep: Low-rank Tucker Representation Model for Multi-dimensional Data Completion

  2025influential citation
• Unsupervised Range-Nullspace Learning Prior for Multispectral Images Reconstruction

  2025cites this paper
• Slice-Wise Irregular Tensor Decomposition and Its Application

  2025cites this paper
• Eigen-CNN: Eigenimages Plus Eigennoise Level Maps Guided Network for Hyperspectral Image Denoising

  2024cites this paper
• Bayesian tensor network structure search and its application to tensor completion

  2024cites this paper
• Enhanced Low-Rank and Sparse Tucker Decomposition For Image Completion

  2024cites this paper
• Multispectral and hyperspectral images fusion based on subspace representation and nonlocal low-rank regularization

  2024cites this paper
• Tensor completion via multi-directional partial tensor nuclear norm with total variation regularization

  2024cites this paper
• Multimode Multiple Relationships Nuclear Norm Minimization Robust PCA Method for IoT Data Restoration

  2024cites this paper
• A Novel Tensor Ring Sparsity Measurement for Image Completion

  2024cites this paper
• 3D Poissonian image deblurring via patch-based tensor logarithmic Schatten-p minimization

  2024cites this paper
• Tensor Robust Kernel PCA for Multidimensional Data

  2024cites this paper
• Removal of Mixed Noise in Hyperspectral Images Based on Subspace Representation and Nonlocal Low-Rank Tensor Decomposition

  2024cites this paper
• Learnable Representative Coefficient Image Denoiser for Hyperspectral Image

  2024cites this paper
• Adaptive weighted robust data recovery with total variation for hyperspectral image

  2024cites this paper
• Hyperspectral Image Denoising via $L_{0}$ Regularized Low-Rank Tucker Decomposition

  2024cites this paper
• Low-rank Tensor Restoration for ERP extraction

  2024cites this paper
• Enhancing photon-counting computed tomography reconstruction via subspace dictionary learning and spatial sparsity regularization

  2024cites this paper
• Nonlocal Gaussian scale mixture modeling for hyperspectral image denoising

  2024cites this paper
• A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring

  2024cites this paper
• Hyperspectral Image Denoising via Double Subspace Deep Prior

  2024cites this paper
• Robust and adaptive subspace learning for fast hyperspectral image denoising

  2024cites this paper
• Cyclic tensor singular value decomposition with applications in low-rank high-order tensor recovery

  2024cites this paper
• LOQUAT: Low-Rank Quaternion Reconstruction for Photon-Counting CT

  2024cites this paper
• Low-rank tensor completion via nonlocal self-similarity regularization and orthogonal transformed tensor Schatten-p norm

  2024cites this paper
• Fast Large-Scale Hyperspectral Image Denoising via Noniterative Low-Rank Subspace Representation

  2024cites this paper
• Low-Rank Tensor Train and Self-Similarity Based Spectral CT Reconstruction

  2024cites this paper
• Revisiting trace norm minimization for tensor Tucker completion: A direct multilinear rank learning approach

  2024cites this paper
• Multi-Dimensional Visual Data Restoration: Uncovering the Global Discrepancy in Transformed High-Order Tensor Singular Values

  2024cites this paper
• Haar Nuclear Norms With Applications to Remote Sensing Imagery Restoration

  2024influential citation
• A nonlinear high-order transformations-based method for high-order tensor completion

  2024cites this paper
• Memory Augmentation and Non-Local Spectral Attention for Hyperspectral Denoising

  2024cites this paper
• Unidirectional Spatial and Spectral Smoothed Tensor Ring Decomposition for Hyperspectral Image Denoising and Destriping

  2024cites this paper
• Dy-mer: An Explainable DNA Sequence Representation Scheme using Sparse Recovery

  2024cites this paper
• Balanced Unfolding Induced Tensor Nuclear Norms for High-Order Tensor Completion

  2024cites this paper
• Spatial–Spectral Oriented Triple Attention Network for Hyperspectral Image Denoising

  2024cites this paper
• Enhanced Low-Rank Tensor Recovery Fusing Reweighted Tensor Correlated Total Variation Regularization for Image Denoising

  2024cites this paper
• Augmented Lagrangian method for tensor low-rank and sparsity models in multi-dimensional image recovery

  2024influential citation
• Nested Fully-Connected Tensor Network Decomposition for Multi-Dimensional Visual Data Recovery

  2024cites this paper
• Smooth Tensor Product for Tensor Completion

  2024cites this paper
• Small Target Detection Method Based on Low-Rank Sparse Matrix Factorization for Side-Scan Sonar Images

  2023cites this paper
• Nonlocal Structured Sparsity Regularization Modeling for Hyperspectral Image Denoising

  2023influential citation
• A new nonconvex low-rank tensor approximation method with applications to hyperspectral images denoising

  2023cites this paper
• Low-Tubal-Rank tensor recovery with multilayer subspace prior learning

  2023cites this paper
• Hyperspectral Image Denoising Via Nonlocal Rank Residual Modeling

  2023cites this paper
• An End-to-End Framework for Joint Denoising and Classification of Hyperspectral Images

  2023influential citation
• Learning Double Subspace Representation for Joint Hyperspectral Anomaly Detection and Noise Removal

  2023cites this paper
• Poissonian Blurred Hyperspectral Imagery Denoising Based on Variable Splitting and Penalty Technique

  2023cites this paper