Results 61 to 70 of about 6,499 (150)

Adaptive blind image deblurring and denoising

Scandinavian Journal of Statistics, Volume 53, Issue 1, Page 413-441, March 2026.
Abstract Blind image deblurring aims to reconstruct the original image from its blurred version without knowing the blurring mechanism. This is a challenging ill‐posed problem because there are infinitely many possible solutions. The ill‐posedness is further exacerbated if the blurring mechanism depends on the pixel location.
Yicheng Kang, Anik Roy, Partha Sarathi Mukherjee   +2 more
wiley   +1 more source

Blind Image Deblurring via Local Maximum Difference Prior

IEEE Access, 2020
Blind image deblurring is a well-known conundrum in the digital image processing field. To get a solid and pleasing deblurred result, reasonable statistical prior of the true image and the blur kernel is required.
Jing Liu, Jieqing Tan, Lei He, Xianyu Ge, Dandan Hu   +4 more
doaj   +1 more source

Image Restoration Using Joint Statistical Modeling in Space-Transform Domain

, 2014
This paper presents a novel strategy for high-fidelity image restoration by characterizing both local smoothness and nonlocal self-similarity of natural images in a unified statistical manner. The main contributions are three-folds.
Gao, Wen, Ma, Siwei, Xiong, Ruiqin, Zhang, Jian, Zhao, Debin   +4 more
core   +1 more source

Multi‐Scale Transformer for Image Restoration

CAAI Transactions on Intelligence Technology, Volume 11, Issue 1, Page 41-54, February 2026.
ABSTRACT Although Transformer‐based image restoration methods have demonstrated impressive performance, existing Transformers still insufficiently exploit multiscale information. Previous non‐Transformer‐based studies have shown that incorporating multiscale features is crucial for improving restoration results.
Wuzhen Shi, Youwei Pan, Chun Zhao, Yuqing Liu, Shaobo Zhang, Heng Zhang, Yang Wen   +6 more
wiley   +1 more source

UG^2: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition

, 2018
Advances in image restoration and enhancement techniques have led to discussion about how such algorithmscan be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and super-resolution should
Banerjee, Sreya, Grm, Klemen, Scheirer, Walter J., Struc, Vitomir, Vidal, Rosaura G.   +4 more
core   +1 more source

Artificial Intelligence Revolution in Transcriptomics: From Single Cells to Spatial Atlases

Advanced Science, Volume 13, Issue 5, 27 January 2026.
Single‐cell RNA sequencing and spatial transcriptomics have unveiled cellular heterogeneity and tissue organization with unprecedented resolution. Artificial intelligence (AI) now plays a pivotal role in interpreting these complex data. This review systematically surveys AI applications across the entire analytic workflow and offers practical guidance ...
Shixin Li, Tianxiang Xiao, Yuanyuan Lan, Chengxiao Wu, Zhouying Li, Rong Liu, Qing Fang, Chao Zhang   +7 more
wiley   +1 more source

Blind Image Deblurring via Reweighted Graph Total Variation

, 2017
Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry
Bai, Yuanchao, Cheung, Gene, Gao, Wen, Liu, Xianming   +3 more
core   +1 more source

Exact, time‐dependent analytical equations for spiral trajectories and matching gradient and density‐correction waveforms

Magnetic Resonance in Medicine, Volume 95, Issue 1, Page 400-410, January 2026.
Abstract Purpose To analytically define a spiral waveform and trajectory that match the constraints of gradient frequency, slew rate, and amplitude. Theory and Methods Piecewise analytical solutions for gradient waveforms under the desired constraints are derived using the circle of an involute rather than an Archimedean spiral.
Guruprasad Krishnamoorthy, James G. Pipe
wiley   +1 more source

A method for deblurring motion blur in visible light images based on improved DeblurGAN [PDF]

Zhihui kongzhi yu fangzhen
This paper focuses on the task of motion deblurring in visible light images by improving and further lightening DeblurGAN, resulting in the model Faster-DeblurGAN.
WANG Bilin
doaj   +1 more source

Faster gradient descent and the efficient recovery of images

, 2013
Much recent attention has been devoted to gradient descent algorithms where the steepest descent step size is replaced by a similar one from a previous iteration or gets updated only once every second step, thus forming a {\em faster gradient descent ...
Ascher, Uri, Huang, Hui
core   +1 more source