no code implementations • 24 May 2023 • Yu-Bang Zheng, Xi-Le Zhao, Junhua Zeng, Chao Li, Qibin Zhao, Heng-Chao Li, Ting-Zhu Huang
To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows us to efficiently solve the TN-SS problem from a regularized modeling perspective, eliminating the repeated structure evaluations.
no code implementations • 2 Mar 2022 • Jin-Ju Wang, Nicolas Dobigeon, Marie Chabert, Ding-Cheng Wang, Ting-Zhu Huang, Jie Huang
In the context of Earth observation, change detection boils down to comparing images acquired at different times by sensors of possibly different spatial and/or spectral resolutions or different modalities (e. g., optical or radar).
no code implementations • 4 Dec 2021 • Tian-Jing Zhang, Liang-Jian Deng, Ting-Zhu Huang, Jocelyn Chanussot, Gemine Vivone
Pansharpening refers to the fusion of a panchromatic image with a high spatial resolution and a multispectral image with a low spatial resolution, aiming to obtain a high spatial resolution multispectral image.
no code implementations • 17 Oct 2021 • Ben-Zheng Li, Xi-Le Zhao, Teng-Yu Ji, Xiong-Jun Zhang, Ting-Zhu Huang
The main idea of this type of methods is exploiting the low-rank structure of frontal slices of the targeted tensor under the linear transform along the third mode.
no code implementations • 17 Oct 2021 • Yun-Yang Liu, Xi-Le Zhao, Guang-Jing Song, Yu-Bang Zheng, Ting-Zhu Huang
In this paper, by leveraging the superior expression of the fully-connected tensor network (FCTN) decomposition, we propose a $\textbf{FCTN}$-based $\textbf{r}$obust $\textbf{c}$onvex optimization model (RC-FCTN) for the RTC problem.
no code implementations • 5 Sep 2021 • Jin-Fan Hu, Ting-Zhu Huang, Liang-Jian Deng
Hyperspectral image has become increasingly crucial due to its abundant spectral information.
no code implementations • ICCV 2021 • Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng, Tian-Jing Zhang
In order to enhance the relationships of inter-branches, dynamic cross feature transfers are embedded into multiple branches to obtain high-resolution representations.
no code implementations • 18 Jun 2020 • Meng Ding, Xiao Fu, Ting-Zhu Huang, Jun Wang, Xi-Le Zhao
This work employs an idea that models spectral images as tensors following the block-term decomposition model with multilinear rank-$(L_r, L_r, 1)$ terms (i. e., the LL1 model) and formulates the HSR problem as a coupled LL1 tensor decomposition problem.
no code implementations • 29 May 2020 • Jin-Fan Hu, Ting-Zhu Huang, Liang-Jian Deng, Tai-Xiang Jiang, Gemine Vivone, Jocelyn Chanussot
In order to alleviate this issue, in this work, we propose a simple and efficient architecture for deep convolutional neural networks to fuse a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HR-MSI), yielding a high-resolution hyperspectral image (HR-HSI).
no code implementations • 14 May 2020 • Meng Ding, Ting-Zhu Huang, Xi-Le Zhao, Tian-Hui Ma
Key words: nonconvex optimization, tensor ring rank, logdet function, tensor completion, alternating direction method of multipliers.
no code implementations • 29 Apr 2020 • Meng Ding, Ting-Zhu Huang, Xi-Le Zhao, Michael K. Ng, Tian-Hui Ma
The TT rank minimization accompany with \emph{ket augmentation}, which transforms a lower-order tensor (e. g., visual data) into a higher-order tensor, suffers from serious block-artifacts.
no code implementations • 16 Sep 2019 • Tai-Xiang Jiang, Michael K. Ng, Xi-Le Zhao, Ting-Zhu Huang
In the literature, the tensor nuclear norm can be computed by using tensor singular value decomposition based on the discrete Fourier transform matrix, and tensor completion can be performed by the minimization of the tensor nuclear norm which is the relaxation of the sum of matrix ranks from all Fourier transformed matrix frontal slices.
no code implementations • 3 Dec 2018 • Yu-Bang Zheng, Ting-Zhu Huang, Xi-Le Zhao, Tai-Xiang Jiang, Teng-Yu Ji, Tian-Hui Ma
Based on it, we define a novel tensor rank, the tensor $N$-tubal rank, as a vector whose elements contain the tubal rank of all mode-$k_1k_2$ unfolding tensors, to depict the correlations along different modes.
no code implementations • 26 Aug 2018 • Ye-Tao Wang, Xi-Le Zhao, Tai-Xiang Jiang, Liang-Jian Deng, Yi Chang, Ting-Zhu Huang
Then, our framework starts with learning the motion blur kernel, which is determined by two factors including angle and length, by a plain neural network, denoted as parameter net, from a patch of the texture component.
3 code implementations • 20 Mar 2018 • Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng, Yao Wang
In this paper, we propose a novel video rain streak removal approach FastDeRain, which fully considers the discriminative characteristics of rain streaks and the clean video in the gradient domain.
4 code implementations • 15 Dec 2017 • Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng
In this paper, we investigate tensor recovery problems within the tensor singular value decomposition (t-SVD) framework.
no code implementations • CVPR 2017 • Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng, Yao Wang
Rain streaks removal is an important issue of the outdoor vision system and has been recently investigated extensively.
no code implementations • 12 Mar 2015 • Liang-Jian Deng, Weihong Guo, Ting-Zhu Huang
We propose a new iterative model for single image super-resolution based on an observation: an image is consisted of smooth components and non-smooth components, and we use two classes of approximated Heaviside functions (AHFs) to represent them respectively.
no code implementations • 24 Dec 2013 • Gang Liu, Ting-Zhu Huang, Xiao-Guang Lv, Jun Liu
To solve this kind of ill-posed problems, a regularization term (i. e., regularizer) should be introduced, under the assumption that the solutions have some specific properties, such as sparsity and group sparsity.
no code implementations • 21 Dec 2013 • Gang Liu, Ting-Zhu Huang, Jun Liu, Xiao-Guang Lv
The total variation (TV) regularization method is an effective method for image deblurring in preserving edges.
no code implementations • 13 Oct 2013 • Jun Liu, Ting-Zhu Huang, Ivan W. Selesnick, Xiao-Guang Lv, Po-Yu Chen
Usually, the high-order total variation (HTV) regularizer is an good option except its over-smoothing property.