Results 71 to 80 of about 2,318 (187)

A Preconditioned Majorization‐Minimization Method for ℓ2$$ {\ell}^2 $$‐ℓq$$ {\ell}^q $$ Minimization

Numerical Linear Algebra with Applications, Volume 33, Issue 3, June 2026.
ABSTRACT The need to minimize a linear combination of an expression that involves an ℓq$$ {\ell}^q $$‐norm of a linear transformation of the computed solution and the ℓ2$$ {\ell}^2 $$‐norm of the residual error arises in image restoration as well as in statistics.
A. Buccini, M. Donatelli, M. Ratto, L. Reichel   +3 more
wiley   +1 more source

Stochastic Blind Motion Deblurring [PDF]

IEEE Transactions on Image Processing, 2015
Blind motion deblurring from a single image is a highly under-constrained problem with many degenerate solutions. A good approximation of the intrinsic image can, therefore, only be obtained with the help of prior information in the form of (often nonconvex) regularization terms for both the intrinsic image and the kernel.
Lei Xiao 0014, James Gregson, Felix Heide, Wolfgang Heidrich   +3 more
openaire   +4 more sources

Progressive Colour Equalisation and Detail Refinement for Underwater Image Enhancement

CAAI Transactions on Intelligence Technology, Volume 11, Issue 3, Page 709-725, June 2026.
ABSTRACT Underwater image enhancement remains a critical challenge in computational vision due to complex distortions caused by wavelength‐dependent light absorption and scattering. This paper introduces CEDFNet, a novel two‐stage framework that leverages advanced computational intelligence techniques for robust and high‐fidelity underwater image ...
Songbai Liu, Jiacheng Huang
wiley   +1 more source

Stabilizing and deblurring atmospheric turbulence [PDF]

2011 IEEE International Conference on Computational Photography (ICCP), 2011
A new approach is proposed to correct geometric distortion and reduce space and time-variant blur in videos that suffer from atmospheric turbulence. We first register the frames to suppress geometric deformation using a B-spline based non-rigid registration method.
ZHU XIANG, MILANFAR PEYMAN
openaire   +3 more sources

Simulated Artifacts and Data Augmentation for Real-World Video Motion Deblurring

IEEE Access
This paper proposes a data augmentation method that simulates artifacts specific to real-world videos as a preprocessing step for applying a deep learning-based video deblurring method to real-world videos.
Sota Moriyama, Kaito Kira, Koichi Ichige
doaj   +1 more source

Photon‐Sphere Modes in Curved Optical Microcavities: A Black‐Hole Analogue Laser

Advanced Science, Volume 13, Issue 28, 18 May 2026.
An optical analogue of a Schwarzschild black hole is realized using curved microcavities that preserve light‐like geodesics. A new family of laser modes confined around the photon sphere is identified alongside conventional whispering‐gallery modes. Analytical theory, numerical simulations, and experiments reveal curvature‐induced confinement, enabling
Chenni Xu, Aswathy Sundaresan, Nazire‐Begüm Kazkal, Clement Lafargue, Lior Zarfaty, Li‐Gang Wang, Ofek Birnholtz, Dominique Decanini, Melanie Lebental, Patrick Sebbah   +9 more
wiley   +1 more source

Deep Learning Integration in Optical Microscopy: Advancements and Applications

Microscopy Research and Technique, Volume 89, Issue 5, Page 791-814, May 2026.
It explores the integration of DL into optical microscopy, focusing on key applications including image classification, segmentation, and computational reconstruction. ABSTRACT Optical microscopy is a cornerstone imaging technique in biomedical research, enabling visualization of subcellular structures beyond the resolution limit of the human eye ...
Pottumarthy Venkata Lahari, Sagnika Dutta, H. Deeksha, Samreen A. Patel, Budheswar Dehury, Nirmal Mazumder   +5 more
wiley   +1 more source

Deep Video Deblurring

CoRR, 2016
Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on aligning nearby frames.
Shuochen Su, Mauricio Delbracio, Jue Wang 0001, Guillermo Sapiro, Wolfgang Heidrich, Oliver Wang   +5 more
openaire   +3 more sources

Joint Non-Local Statistical and Wavelet Tight Frame Information-Based ℓ₀ Regularization Model for Image Deblurring

IEEE Access
The 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

Next Generation 7 Tesla Arterial Spin Labeling With Rotated Spiral Acquisition Enables Mesoscale Resolution in 3D Brain Perfusion and Functional MRI

Magnetic Resonance in Medicine, Volume 95, Issue 5, Page 2702-2717, May 2026.
ABSTRACT Purpose To achieve high resolution (≤ 1 mm isotropic) whole‐brain perfusion imaging at 7 T with next generation ASL pulse sequence, reconstruction algorithm, and MRI hardware. Methods We capitalized on three major innovations: (1) FLASH‐based pseudo‐Continuous ASL (pCASL) sequence with rotated golden‐angle stack‐of‐spirals (rGA‐SoS) sampling; (
Chenyang Zhao, Fanhua Guo, Zidong Yang, Xingfeng Shao, Samantha J. Ma, Alexander J. S. Beckett, An T. Vu, David A. Feinberg, Danny J. J. Wang   +8 more
wiley   +1 more source