Application of Deep Learning in Blind Motion Deblurring: Current Status and Future Prospects

Y Xiang, H Zhou, C Li, F Sun, Z Li, Y Xie - arXiv preprint arXiv:2401.05055, 2024 - arxiv.org
Motion deblurring is one of the fundamental problems of computer vision and has received
continuous attention. The variability in blur, both within and across images, imposes …

All-in-one multi-degradation image restoration network via hierarchical degradation representation

C Zhang, Y Zhu, Q Yan, J Sun, Y Zhang - Proceedings of the 31st ACM …, 2023 - dl.acm.org
The aim of image restoration is to recover high-quality images from distorted ones. However,
current methods usually focus on a single task (eg, denoising, deblurring or super …

Perceptual Decoupling with Heterogeneous Auxiliary Tasks for Joint Low-Light Image Enhancement and Deblurring

Y Li, R Xu, Y Niu, W Guo, T Zhao - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Capturing images at night are susceptible to inadequate illumination conditions and motion
blurring. Given the typical coupling of these two forms of degradation, a pioneer work takes a …

Image blind motion deblurring method with longitudinal channel and wavelet dynamic convolution

N Jiang, Y Zhang, F Yan, X Fu, T Kong - Computers & Graphics, 2023 - Elsevier
Deep learning methods have achieved great success in image deblurring. However, these
methods also exist two limitations, the detailed information loss caused by the image …

Towards Extreme Image Rescaling with Generative Prior and Invertible Prior

H Wei, C Ge, Z Li, X Qiao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The goal of image rescaling is to embed the information from high-resolution images into
low-resolution images and then reconstruct the high-resolution images in reverse. Existing …

RUN: Rethinking the UNet Architecture for Efficient Image Restoration

Z Wu, J Li, C Xu, D Huang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recent advanced image restoration (IR) methods typically stack homogeneous operators
hierarchically in the UNet architecture. To achieve higher accuracy, these models are now …

Improvement of lithium battery corner detection accuracy based on image restoration method

H Cheng, Q Bi, X Chen, H Zheng, Y Du, Z Jiang - Physica Scripta, 2024 - iopscience.iop.org
Target detection technology has been widely used in the automatic production of lithium
batteries. However, motion blur will lead to the reduction of the angular position detection …

How to deal with glare for improved perception of Autonomous Vehicles

MZ Alam, Z Kaleem, S Kelouwani - arXiv preprint arXiv:2404.10992, 2024 - arxiv.org
Vision sensors are versatile and can capture a wide range of visual cues, such as color,
texture, shape, and depth. This versatility, along with the relatively inexpensive availability of …

[引用][C] 图像去模糊研究综述

胡张颖, 周全, 陈明举, 崔景程, 吴晓富, 郑宝玉 - 中国图象图形学报, 2024