Results 51 to 60 of about 441,411 (171)

A Motion Deblur Method Based on Multi-Scale High Frequency Residual Image Learning

IEEE Access, 2020
Non-uniform blind deblurring of dynamic scenes has always been a challenging problem in image processing because of the diverse of blurring sources. Traditional methods based on energy minimization cannot make accurate kernel estimation. It leads to that
Keng-Hao Liu, Chia-Hung Yeh, Juh-Wei Chung, Chuan-Yu Chang   +3 more
doaj   +1 more source

Noise-Adaptive Non-Blind Image Deblurring

Sensors, 2022
This work addresses the problem of non-blind image deblurring for arbitrary input noise. The problem arises in the context of sensors with strong chromatic aberrations, as well as in standard cameras, in low-light and high-speed scenarios.
Michael Slutsky
doaj   +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

Blind Remote Sensing Image Deblurring Based on Local Maximum High-Frequency Coefficient Prior and Graph Regularization

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In satellite remote sensing imaging, factors such as optical axis shift, image plane jitter, movement of the target object, and Earth's rotation can induce image blur.
Zhidan Cai, Ming Fang, Zhe Li, Jinyi Ming, Huimin Wang   +4 more
doaj   +1 more source

ESFFA: Early‐Stage Feature Frequency Attack in Cross‐Domain Few‐Shot Learning

IET Computer Vision, Volume 20, Issue 1, January/December 2026.
This paper addresses the challenge of cross‐domain few‐shot learning (CD‐FSL), where models often rely on frequency shortcuts rather than semantic features. We propose ESFFA (Early‐Stage Feature Frequency Attack), a novel method that perturbs low‐frequency statistics and masks high‐frequency components in shallow feature maps to reduce shortcut ...
Xu Wang, Ziyang Cao, Jia Zhao, Huiling Wang, Yingzhou Chen   +4 more
wiley   +1 more source

Single Image Defocus Deblurring Based on Structural Information Enhancement

IEEE Access
Defocus deblurring is an important task in computer vision that aims to bring images back to clarity. Over recent years, both blind defocuse deblurring and non-blind defocuse deblurring methods have made great progress in the single image defocus ...
Guangming Feng, Longfei Han, Yiwen Jia, Peiliang Huang   +3 more
doaj   +1 more source

Blind Deblurring Using Space Target Features

IEEE Access, 2019
The star image suffers inevitably from degradation due to the high-speed motion of the space target and the long exposure time of the camera, therefore the attitude information of the star is hard to accurately obtain.
Peiyu Liu, Yan Zhao, Wenbo Yang, Shigang Wang, Shu Chen   +4 more
doaj   +1 more source

Hybrid Deep Learning Frameworks for License Plate Recognition in Complex Environments: A Comprehensive Survey and Research Outlook

IET Computer Vision, Volume 20, Issue 1, January/December 2026.
This survey systematically reviews state‐of‐the‐art license plate recognition methods, with a focus on hybrid CNN‐transformer frameworks and the joint optimisation of detection and recognition for real‐world deployment. It further analyses existing datasets, highlights persistent challenges, such as domain generalisation, and outlines pathways towards ...
SanXing Deng, Ewe Lay Sheng, Tiong Sieh Kiong, MengMeng Yang   +3 more
wiley   +1 more source

Real-time Blind Deblurring Based on Lightweight Deep-Wiener-Network

, 2023
In this paper, we address the problem of blind deblurring with high efficiency. We propose a set of lightweight deep-wiener-network to finish the task with real-time speed.
Yu, Yang, Li, Runjia, Haywood, Charlie
core  

Enhancing convolutional neural network generalizability via low‐rank weight approximation

IET Image Processing, Volume 20, Issue 1, January/December 2026.
A self‐supervised framework is proposed for image denoising based on the Tucker low‐rank tensor approximation. With the proposed design, we are able to characterize our denoiser with fewer parameters and train it based on a single image, which considerably improves the model's generalizability and reduces the cost of data acquisition. Abstract Noise is
Chenyin Gao, Shu Yang, Anru R. Zhang
wiley   +1 more source