Filters








3,127 Hits in 6.3 sec

Nonlinear fractional diffusion model for deblurring images with textures

Zhichang Guo, ,School of Mathematics, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China, Wenjuan Yao, Jiebao Sun, Boying Wu
2019 Inverse Problems and Imaging  
In the new model, a fractional gradient is used for regularization of the diffusion process to preserve texture features and a source term with blurring kernel is used for deblurring.  ...  In order to deal with this challenging but imperative issue, we establish a framework of nonlinear fractional diffusion equations, which performs well in deblurring images with textures.  ...  The authors thank Yiqiu Dong for providing the reference code of her model.  ... 
doi:10.3934/ipi.2019052 fatcat:lnk655oymbaepi7scutjbe4euq

Image Deblurring in the Presence of Impulsive Noise

Leah Bar, Nahum Kiryati, Nir Sochen
2006 International Journal of Computer Vision  
Distinguishing outliers from edge elements is difficult in current gradient-based edge-preserving restoration methods.  ...  Data fidelity is quantified using the robust modified L 1 norm, and elements from the Mumford-Shah functional are used for regularization.  ...  Acknowledgment This research was supported by MUSCLE: Multimedia Understanding through Semantics, Computation and Learning, a European Network of Excellence funded by the EC 6th Frame-  ... 
doi:10.1007/s11263-006-6468-1 fatcat:43m7qgw555c7jaq4dgt5oermky

On learning optimized reaction diffusion processes for effective image restoration

Yunjin Chen, Wei Yu, Thomas Pock
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
For several decades, image restoration remains an active research topic in low-level computer vision and hence new approaches are constantly emerging.  ...  Experiments show that our trained nonlinear reaction diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for image  ...  In a latter work [42] , the theoretical foundations for discrete forward-andbackward diffusion filtering were investigated.  ... 
doi:10.1109/cvpr.2015.7299163 dblp:conf/cvpr/ChenYP15 fatcat:ktvc4sb7xbcbnjptrgf3r6peeq

Theoretical Foundations of Anisotropic Diffusion in Image Processing [chapter]

J. Weickert
1996 Computing Supplement  
Their theoretical foundations are treated in Chapters 2-4. PREFACE vii such that it should contain interesting material for many readers.  ...  The subsequent three chapters explore a theoretical framework for anisotropic diffusion filtering.  ...  On the other hand, nonlinear diffusion filters are frequently applied with very impressive results; so there appears the need for a theoretical foundation.  ... 
doi:10.1007/978-3-7091-6586-7_13 dblp:conf/tfcv/Weickert94 fatcat:pu7ukgair5c63fzkkew3rq7tya

Multi-layer Basis Pursuit for Compressed Sensing MR Image Reconstruction

Abdul Wahid, Jawad Shah, Adnan Umar Khan, Manzoor Ahmed, Hanif Razali
2020 IEEE Access  
Saiprasad Ravishankar for providing data for the CS-MRI analysis.  ...  Authors would like to thank Electronics Section, Universiti Kuala Lumpur British Malaysia Institute, Radiology department Hospital Kuala Lumpur (HKL), and the higher education commission of Pakistan for  ...  ML-CSC AS THEORETICAL FOUNDATION FOR DEEP LEARNING The heuristic techniques applied to problems in deep learning frameworks have been recently investigated for theoretical explanations of deep learning  ... 
doi:10.1109/access.2020.3028877 fatcat:wdbm7fsngjgu5m5aaauudqsdze

A Novel Gray Image Denoising Method Using Convolutional Neural Network

Yizhen Meng, Jun Zhang
2022 IEEE Access  
Total variation regularization combined with the power of structure tensor adaptiveness provided better edge preserving image denoising. Dang et al.  ...  Image restoration with adaptive weight-based total variation regularization model was proposed in [91] .  ... 
doi:10.1109/access.2022.3169131 fatcat:uom37pgrk5hebmasts4jamwj2q

Underwater Image Restoration Based on a Parallel Convolutional Neural Network

Keyan Wang, Yan Hu, Jun Chen, Xianyun Wu, Xi Zhao, Yunsong Li
2019 Remote Sensing  
In this paper, we propose an effective convolutional neural network (CNN) for underwater image restoration.  ...  edge features.  ...  Therefore, after estimating the transmission map, the edge-preserving filter is often used for refinement.  ... 
doi:10.3390/rs11131591 fatcat:k727hrcapbbzneujn3gre6e7ly

Regularization Parameter Selection for Nonlinear Iterative Image Restoration and MRI Reconstruction Using GCV and SURE-Based Methods

S. Ramani, Zhihao Liu, J. Rosen, J. Nielsen, J. A. Fessler
2012 IEEE Transactions on Image Processing  
We apply the methods to image restoration and to magnetic resonance image (MRI) reconstruction using total variation (TV) and an analysistype ℓ 1 -regularization.  ...  We also observed that minimizing GCV yields reconstruction results that are near-MSE-optimal for image restoration and slightly sub-optimal for MRI.  ...  Synthesis formulations preclude popular regularization criteria such as total variation (TV) and smooth edge-preserving regularizers (e.g., Huber [39] , smoothed-Laplacian [40] ) that belong to the class  ... 
doi:10.1109/tip.2012.2195015 pmid:22531764 pmcid:PMC3411925 fatcat:3ftuhlzuffezzbqlyhsqznzbkm

Unsupervised, information-theoretic, adaptive image filtering for image restoration

S.P. Awate, R.T. Whitaker
2006 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Image restoration is an important and widely studied problem in computer vision and image processing.  ...  In this way, UINTA automatically discovers the statistical properties of the signal and can thereby restore a wide spectrum of images.  ...  ACKNOWLEDGMENTS This work was supported by US National Science Foundation (NSF) EIA0313268 and NSF CAREER CCR0092065 grants.  ... 
doi:10.1109/tpami.2006.64 pmid:16526423 fatcat:i3b6tzufp5gzhoziq2gwfcqzru

Nonlinear backprojection for tomographic reconstruction

B.I. Andia, K.D. Sauer, C.A. Bouman
2002 IEEE Transactions on Nuclear Science  
This work focuses on a tomographic image reconstruction method which will be referred to as nonlinear backprojection (NBP).  ...  Rather than explicitly statistically modeling the forward process and the unknown image, we train an optimal nonlinear backprojection operator which can be implemented non-iteratively.  ...  Nonlinear £lters used for heart image of Fig. 6. The £lters were obtained by training on a synthetic heart image. Figure 8 :Figure 9 : 89 Nonlinear £lters used for heart image ofFig. 9.  ... 
doi:10.1109/tns.2002.998682 fatcat:dfkdjtrbwbdztb7jrmjwisffge

On learning optimized reaction diffusion processes for effective image restoration [article]

Yunjin Chen, Wei Yu, Thomas Pock
2015 arXiv   pre-print
For several decades, image restoration remains an active research topic in low-level computer vision and hence new approaches are constantly emerging.  ...  Experiments show that our trained nonlinear reaction diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for image  ...  In a latter work [41] , the theoretical foundations for discrete forward-andbackward diffusion filtering were investigated.  ... 
arXiv:1503.05768v2 fatcat:kd2fio43fbeu7mtp3nmcpl26xa

Adaptive Image Denoising Method Based on Diffusion Equation and Deep Learning

Shaobin Ma, Lan Li, Chengwen Zhang, Shan Zhong
2022 Journal of Robotics  
, so as to further preserve the important details of the image such as edge and texture.  ...  Effective noise removal has become a hot topic in image denoising research while preserving important details of an image.  ...  Acknowledgments is study was supported by the Industrial Support and Guidance Project of Colleges and Universities in Gansu Province: Research and implementation of digital comprehensive display system for  ... 
doi:10.1155/2022/7115551 fatcat:yciorhh6xrcezljfnramn54ici

Low-Light Maritime Image Enhancement with Regularized Illumination Optimization and Deep Noise Suppression [article]

Yu Guo, Yuxu Lu, Ryan Wen Liu, Meifang Yang, Kwok Tai Chui
2020 arXiv   pre-print
To promote imaging performance, it is necessary to restore the important visual information from degraded low-light images.  ...  To suppress the effect of unwanted noise on imaging performance, a deep learning-based blind denoising framework is further introduced to promote the visual quality of enhanced image.  ...  To further improve imaging performance, a low-light image enhancement algorithm for non-uniform illumination images [21] has been proposed to restore the details and preserve the naturalness.  ... 
arXiv:2008.03765v1 fatcat:gdzwattbqndsbduacm26fqnymq

Dual-energy CT Reconstruction from Dual Quarter Scans [article]

Wenkun Zhang, Ningning Liang, Linyuan Wang, Ailong Cai, Zhizhong Zheng, Chao Tang, Yizhong Wang, Lei Li, Bin Yan, Guoen Hu
2020 arXiv   pre-print
This strategy largely reduces the limited-angle artifacts and preserves the image edges and inner structures.  ...  Utilizing the capability of neural network in the modeling of nonlinear problem, a novel Anchor network with single-entry double-out architecture is designed in this work to yield the desired DECT images  ...  The fusion CT image is shown in this work to reveal its specify effectiveness in artifact suppression and edge preservation.  ... 
arXiv:2012.11374v1 fatcat:zmabttujevb4zo4bpmhtl7lrvm

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

Franziska Schirrmacher, Thomas Köhler, Christian Riess
2020 arXiv   pre-print
Inverse problems play a central role for many classical computer vision and image processing tasks. Many inverse problems are ill-posed, and hence require a prior to regularize the solution space.  ...  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.  ...  Acknowledgment This work was supported in part by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) Project number 146371743 TRR 89 Invasive Computing  ... 
arXiv:1804.02152v2 fatcat:qtreganjhnbwveyflauabpb7lq
« Previous Showing results 1 — 15 out of 3,127 results