Results 41 to 50 of about 12,142,372 (124)
An image defocus deblurring method based on gradient difference of boundary neighborhood
Virtual Reality & Intelligent Hardware, 2023 Background: For static scenes with multiple depth layers, the existing defocused image deblurring methods have the problems of edge ringing artifacts or insufficient deblurring degree due to inaccurate estimation of blur amount, In addition, the prior ...
Junjie TAO +6 more
doaj +1 more source
Magnetic Resonance in Medicine, EarlyView.ABSTRACT Purpose Gap‐filled zero echo time (ZTE) acquisitions combined with dedicated short‐T2 hardware enable direct collagen imaging on the timescale of macromolecular (MM) signals, with T2s ˜ 10 μs. However, present methods offer limited depiction fidelity, and their specificity towards MM content is poorly understood. This work presents methodology
Jason Daniel van Schoor +3 more
wiley +1 more source
Image deblurring comparison for synthetic images.
, 2018 (a) denotes the input image and real blur kernel. (b) denotes the matched exemplar. (c) denotes the predicted ∇S. (d)—(j) denote the deblurring results of Krishnan[12], Xu eta.[17], Shan[15], Xu & Jia[7], Levin[16], Pan[9] and our method, respectively ...
Houjie Li (4918960) +4 more
core +1 more source
IEEE AccessThe task of image deblurring is a complex and ill-posed inverse problem, which endeavors to restore a high-fidelity image from its degraded and blurred counterpart.
Yongqun Tan, Lingli Zhang, Yu Chen
doaj +1 more source
Image deblurring method driven by double layer convolution neural network denoising module
Nantong Daxue xuebao. Ziran kexue ban, 2022 To solve this problem for inflexible of noise levels for deep convolution neural network for image denoising, an image deblurring method driven by a double deep convolution neural network for image denoising is proposed.The learning capability of ...
WU Jingjing; MA Jingning; ZHU Yonggui
doaj +1 more source
Accelerated MR Elastography Using Learned Neural Network Representation
Magnetic Resonance in Medicine, EarlyView.ABSTRACT Purpose To develop a deep‐learning method for achieving fast high‐resolution MR elastography from highly undersampled data without the need for high‐quality training datasets. Methods We first reframed the deep neural network representation as a nonlinear extension of the linear subspace model, then used it to represent and reconstruct MRE ...
Xi Peng
wiley +1 more source
A Fractional-Order Fidelity-Based Total Generalized Variation Model for Image Deblurring
Fractal and Fractional, 2023 Image deblurring is a fundamental image processing task, and research for efficient image deblurring methods is still a great challenge. Most of the currently existing methods are focused on TV-based models and regularization term construction; little ...
Juanjuan Gao +3 more
doaj +1 more source
A user‐friendly platform for deep‐learning‐based image enhancement in scanning X‐ray microscopy
Journal of Synchrotron Radiation, EarlyView.A graphical user interface is developed for deep‐learning‐based image enhancement in scanning X‐ray microscopy. By incorporating the intensity of the probe and scan parameters, the graphical user interface enables accessible and reproducible super‐resolution and deblurring of scanning X‐ray datasets, supporting improved analysis of X‐ray fluorescence ...
Xiaoyin Zheng +7 more
wiley +1 more source
Computer Graphics Forum, EarlyView.Abstract Correlation‐based rendering techniques continue to advance, and efficiently exploiting correlations between pixel estimates has become increasingly important. The deep combiner framework [BHHM20] allows us to fuse independent and correlated pixel estimates but focuses solely on spatial correlations.
W. Zhou, E. Hughes, T. Hachisuka
wiley +1 more source
Application of Polynomial Transforms in Image Deblurring
, 1989 In this paper, we present an algorithm for deblurring and interpolating digital images. Deblurring is an ill-posed problem, which can be made well-behaved by introducing assumptions about the input image.
Martens, J.B.O.S. (Jean-Bernard) +1 more
core +1 more source