Spectral Total Variation

Spectral Total Variation (STV) is a mathematical framework used to enhance the quality and analysis of multispectral and hyperspectral images by leveraging both spatial and spectral information. Current research focuses on improving STV-based models for image restoration tasks like denoising and fusion, often employing advanced optimization techniques such as primal-dual splitting methods and incorporating additional regularizations like low-rank and sparsity constraints to better capture image structure. These advancements lead to improved image quality metrics and enable more accurate analysis of hyperspectral data in applications such as remote sensing and medical imaging. The development of more robust and efficient STV methods is crucial for advancing these fields.

Papers

March 19, 2024

Multispectral Image Restoration by Generalized Opponent Transformation Total Variation
Zhantao Ma, Michael K. Ng
Image Restoration Multispectral Image Total Variation Multispectral Satellite Spectral Total Variation

September 24, 2022

Robust Hyperspectral Image Fusion with Simultaneous Guide Image Denoising via Constrained Convex Optimization
Saori Takeyama, Shunsuke Ono
Image Fusion Primal Dual Spatial Resolution Joint Denoising Constrained Convex Optimization Image Estimation Spectral Total Variation

July 22, 2022

Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising
Shingo Takemoto, Kazuki Naganuma, Shunsuke Ono
Graph Drawing Hyperspectral Image Total Variation Hyperspectral Image Denoising Noise Removal Spectral Total Variation

April 27, 2022

Low-rank Meets Sparseness: An Integrated Spatial-Spectral Total Variation Approach to Hyperspectral Denoising
Haijin Zeng, Shaoguang Huang, Yongyong Chen, Hiep Luong, Wilfried Philips
Hyperspectral Image Many Sparse Low Rank Hyperspectral Image Denoising Spectral Total Variation Gradient Tensor

January 8, 2022

Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization
Chong Peng, Yang Liu, Yongyong Chen, Xinxin Wu, Andrew Cheng, Zhao Kang, Chenglizhao Chen, Qiang Cheng
Low Rank Non Convex Hyperspectral Image Denoising Sparse Mixture Robust Principal Component Analysis HSI Denoising Shrinkage Estimator Spectral Total Variation

Spectral Total Variation

Papers

Multispectral Image Restoration by Generalized Opponent Transformation Total Variation

Robust Hyperspectral Image Fusion with Simultaneous Guide Image Denoising via Constrained Convex Optimization

Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising

Low-rank Meets Sparseness: An Integrated Spatial-Spectral Total Variation Approach to Hyperspectral Denoising

Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization