316 Hits in 6.3 sec

Depth image denoising using nuclear norm and learning graph model [article]

Chenggang Yan, Zhisheng Li, Yongbing Zhang, Yutao Liu, Xiangyang Ji, Yongdong Zhang
2020 arXiv   pre-print
In this paper, considering that group-based image restoration methods are more effective in gathering the similarity among patches, a group based nuclear norm and learning graph (GNNLG) model was proposed  ...  impose the smoothing priors to the denoised depth image.  ...  CONCLUSION This paper builds a novel framework for depth image denoising using the group-based nuclear norm and learning graph(GNNLG) model, which exploits the intrinsic low-rank and self-similarity property  ... 
arXiv:2008.03741v1 fatcat:wnr4llyikvbxflfaluxkyhngom

Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms [article]

Yanna Bai, Wei Chen, Jie Chen, Weisi Guo
2020 arXiv   pre-print
We review how deep learning methods are used in solving different linear inverse problems, and explore the structured neural network architectures that incorporate knowledge used in traditional methods  ...  Furthermore, we identify open challenges and potential future directions along this research line.  ...  One popular approach is to use tensor nuclear norm M * , which is a convex combination of the nuclear norms of all matrices unfolded along different modes [27] .  ... 
arXiv:2007.13290v2 fatcat:kqoerts77nftbl32fctx3za2me

A Novel Gray Image Denoising Method Using Convolutional Neural Network

Yizhen Meng, Jun Zhang
2022 IEEE Access  
Then, the regularization with nonconvex penalty function and its weighted version are used to replace the nuclear norm and entry-wise L1 norm in original RPCA, respectively, to establish an improved model  ...  [75] defined relative total variation Weighted nuclear norm minimization (WNNM) with total variation (RTV), A relative Total variation and Weighted Nuclear norm minimization (RTV-WNNM) is proposed by  ... 
doi:10.1109/access.2022.3169131 fatcat:uom37pgrk5hebmasts4jamwj2q

Nonlocal Spectral Prior Model for Low-Level Vision [chapter]

Shenlong Wang, Lei Zhang, Yan Liang
2013 Lecture Notes in Computer Science  
We consequently apply the NSP model to typical image restoration tasks, including denoising, superresolution and deblurring, and the experimental results demonstrated the highly competitive performance  ...  attention to describe and utilize the image nonlocal self-similarities.  ...  SVD is used to get the nuclear norm of all nonlocal matrices. We then cluster the central patch of each nonlocal matrix by using Gaussian mixture model with 50 components.  ... 
doi:10.1007/978-3-642-37431-9_18 fatcat:6zuio5ik3nfdfk7ewvuo2mzhxe

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 8055-8068 Graph theory 3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model.  ...  ., +, TIP 2020 100-115 Low-Rank Approximation via Generalized Reweighted Iterative Nuclear and Frobenius Norms.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Table of contents

2020 IEEE Transactions on Image Processing  
Zhu3254 3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model ........... ........................................................................... J.  ...  Xue, and Q. Liao 1450 Receptive Field Size Versus Model Depth for Single Image Super-Resolution ....... R. Wang, M. Gong, and D.  ...  Lin, and Zhang, Y. Tian, K. Wang, W. Zhang, and F.-  ... 
doi:10.1109/tip.2019.2940373 fatcat:i7hktzn4wrfz5dhq7hj75u6esa

Adaptive Quantile Sparse Image (AQuaSI) Prior for Inverse Imaging Problems [article]

Franziska Schirrmacher, Thomas Köhler, Christian Riess
2020 arXiv   pre-print
We demonstrate the efficacy of the proposed prior in joint RGB/depth upsampling, on RGB/NIR image restoration, and in a comparison with related regularization by denoising approaches.  ...  It is based on a quantile filter, can be used as a joint filter on guidance data, and be readily plugged into a wide range of numerical optimization algorithms.  ...  For that use case, we compare AQuaSI in its dynamic guidance mode to different well known stand-alone image denoising methods, namely weighted nuclear norm minimization (WNN) [8] , color block-matching  ... 
arXiv:1804.02152v2 fatcat:qtreganjhnbwveyflauabpb7lq

Group Sparsity Residual Constraint for Image Denoising [article]

Zhiyuan Zha, Xinggan Zhang, Qiong Wang, Lan Tang, Xin Liu
2017 arXiv   pre-print
Unlike the conventional group-based sparse representation denoising methods, two kinds of prior, namely, the NSS priors of noisy and pre-filtered images, are used in GSRC.  ...  To this end, we first obtain a good estimation of the group sparse coefficients of the original image by pre-filtering, and then the group sparse coefficients of the noisy image are used to approximate  ...  Depth map denoising using graph- for removing mixed noise in image[J].  ... 
arXiv:1703.00297v6 fatcat:obxufquw6jajxlqmrqvsz4cf2e

GraFT: Graph Filtered Temporal Dictionary Learning for Functional Neural Imaging [article]

Adam S. Charles, Nathan Cermak, Rifqi Affan, Ben Scott, Jackie Schiller, Gal Mishne
2021 bioRxiv   pre-print
Specifically, we focus on the time-traces, which are the main quantity used in scientific discovery, and learn the dictionary of time traces with the spatial maps acting as the presence coefficients encoding  ...  Furthermore, we present a novel graph filtering model which redefines connectivity between pixels in terms of their shared temporal activity, rather than spatial proximity.  ...  ACKNOWLEDGMENTS The authors thank Samuel Schickler for running the comparison experiment of Suite2p on sparse dendritic imaging.  ... 
doi:10.1101/2021.05.24.445514 fatcat:sd5xnohetra37odabihnphs6fi

Gradient and Multi Scale Feature Inspired Deep Blind Gaussian Denoiser

Ramesh Kumar Thakur, Suman Kumar Maji
2022 IEEE Access  
The feature denoising block used in the middle of the first module enhances the feature information of the intermediate image.  ...  Experimental results show superior denoising performance of the proposed method in comparison to several state of the art classical and learning based blind denoising methods like EPLL, BM3D, WNNM, DnCNN  ...  In frequency domain approaches, WNNM [18] is one of the most popular approach where in the authors proposed a weighted nuclear norm minimization-based image denoising approach by exploiting the nonlocal  ... 
doi:10.1109/access.2022.3162608 fatcat:xrisstdogjfsbb3lpqcuahq5ci

Table of Contents [EDICS]

2021 IEEE Transactions on Computational Imaging  
Unger, and C. Guillemot Statistical Image Models CAS: Correlation Adaptive Sparse Modeling for Image Denoising . . . . . . . . . . . . . . . . . . . ..H. Liu, J. Zhang, and R.  ...  Wu Learning-Based Models Graph Convolutional Networks for Model-Based Learning in Nonlinear Inverse Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tci.2022.3143315 fatcat:ul2dbyjijvh7ha44zeuftxanfi

Table of contents

2020 IEEE Transactions on Image Processing  
Qiu 3458 3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model ........... ........................................................................... J.  ...  Fu, and L. Ren 1654 Receptive Field Size Versus Model Depth for Single Image Super-Resolution ....... R. Wang, M. Gong, and D.  ... 
doi:10.1109/tip.2019.2940372 fatcat:h23ul2rqazbstcho46uv3lunku

Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

Qiangqiang Yuan, Qiang Zhang, Jie Li, Huanfeng Shen, Liangpei Zhang
2018 IEEE Transactions on Geoscience and Remote Sensing  
Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications.  ...  In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional  ...  For example, non-local self-similarity (NSS) based methods such as block-matching and 3-D filtering (BM3D) [20] and weighted nuclear norm minimization (WNNM) [21] or learning-based methods such as  ... 
doi:10.1109/tgrs.2018.2865197 fatcat:nnt4rmfzxbceldmpr6toi3fcdi

Edge-guided second-order total generalized variation for Gaussian noise removal from depth map

Shuaihao Li, Bin Zhang, Xinfeng Yang, Weiping Zhu
2020 Scientific Reports  
Total generalized variation models have recently demonstrated high-quality denoising capacity for single image. In this paper, we present an accurate denoising method for depth map.  ...  We use the first-order primal–dual algorithm to minimize the proposed energy function and achieve high-quality denoising and edge preserving result for depth maps with high -intensity noise.  ...  of image u , which is used for image denoising.  ... 
doi:10.1038/s41598-020-73342-3 pmid:33004951 fatcat:3wovpulourb7tir2btrge64lpu

Image De-noising with Machine Learning: A Review

Rini Smita Thakur, Shubhojeet Chatterjee, Ram Narayan Yadav, Lalita Gupta
2021 IEEE Access  
This paper explores the numerous state-of-the-art machine-learning-based image de-noisers like dictionary learning models, convolutional neural networks and generative adversarial networks for a range  ...  It is used to attenuate the noises and accentuate the specific image information stored within.  ...  The data-fidelity term uses -norm fidelity to fit image patches and -norm regularizar for the sparse coding.  ... 
doi:10.1109/access.2021.3092425 fatcat:xirq6soukzchvaeiugcpgxnlqi
« Previous Showing results 1 — 15 out of 316 results