Results 81 to 90 of about 4,539 (201)
FCUnet: An Underwater Image Enhancement Hybrid Network via Fused Feature‐Guided Cross‐Attention
IET Image Processing, Volume 19, Issue 1, January/December 2025.This paper proposes a hybrid CNN‐transformer network for enhancing underwater images. Our approach integrated cross‐attention into the U‐shaped structure with fused feature guidance, designing a colour deviation preprocessing module, a feature fusion unit and a multi‐term loss function to enhance feature extraction capability and adaptability of the ...
Jie Zhu +4 more
wiley +1 more source
Efficient Adjoint Computation for Wavelet and Convolution Operators
, 2016 First-order optimization algorithms, often preferred for large problems, require the gradient of the differentiable terms in the objective function. These gradients often involve linear operators and their adjoints, which must be applied rapidly.
Becker, Stephen, Folberth, James
core +1 more source
Neural‐network‐based regularization methods for inverse problems in imaging
GAMM-Mitteilungen, Volume 47, Issue 4, November 2024.Abstract This review provides an introduction to—and overview of—the current state of the art in neural‐network based regularization methods for inverse problems in imaging. It aims to introduce readers with a solid knowledge in applied mathematics and a basic understanding of neural networks to different concepts of applying neural networks for ...
Andreas Habring, Martin Holler
wiley +1 more source
Blind Deblurring via a Novel Recursive Deep CNN Improved by Wavelet Transform
IEEE Access, 2018 Blind image deconvolution is an ill-posed problem, which is mainly addressed by the regularization methods. Wavelet transform is an effective denoising method related to regularized inversion. In this paper, wavelet transform is utilized to decompose and
Chao Min +3 more
doaj +1 more source
Automatic Estimation of Modulation Transfer Functions
, 2018 The modulation transfer function (MTF) is widely used to characterise the performance of optical systems. Measuring it is costly and it is thus rarely available for a given lens specimen.
Bauer, Matthias +3 more
core +1 more source
Deep learning informed diffusion equation model for image denoising
IET Image Processing, Volume 18, Issue 13, Page 4310-4327, 13 November 2024.The paper presents a Deep Learning Informed Diffusion Equation (DLI‐DE) framework for image denoising, which integrates CNN‐derived image priors into diffusion equations to avoid artifacts common with conventional CNN methods. The uniqueness of the DLI‐DE solution ensures artifact‐free and high‐quality denoising, with performance comparable to advanced
Yao Li +3 more
wiley +1 more source
Fast Blind Image Deblurring Using Smoothing-Enhancing Regularizer
IEEE Access, 2019 Blind deconvolution is a highly ill-posed problem for the restoration of degraded images and requires prior knowledge or regularization. Recently, various priors have been proposed and the models based on these priors have achieved state-of-the-art ...
Zeyang Dou +3 more
doaj +1 more source
Computer-Aided Civil and Infrastructure Engineering, Volume 39, Issue 22, Page 3412-3434, 15 November 2024.Abstract Advancements in infrastructure management have significantly benefited from automatic pavement crack detection systems, relying on image processing enhanced by high‐resolution imaging and machine learning. However, image and motion blur substantially challenge the accuracy of crack detection and analysis.
Yu Zhang, Lin Zhang
wiley +1 more source
ExposureNet: Mobile camera exposure parameters autonomous control for blur effect prevention
IET Image Processing, Volume 18, Issue 12, Page 3403-3414, 16 October 2024.The ExposureNet project addresses the issue of image blur caused by imbalanced camera exposure settings, by developing an autonomous system for controlling these settings. The system, trained comprehensively, predicts ideal exposure based on the semantic features of a scene, using only shutter speed and ISO as training signals.
Abdelwahed Nahli +6 more
wiley +1 more source
Blind Motion Deblurring through SinGAN Architecture
, 2020 Blind motion deblurring involves reconstructing a sharp image from an observation that is blurry. It is a problem that is ill-posed and lies in the categories of image restoration problems. The training data-based methods for image deblurring mostly involve training models that take a lot of time.
Jain, Harshil +3 more
openaire +2 more sources