Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Heterogeneous neural blind deconvolution: A signal processing-empowered foundation feature extractor for bearing fault diagnosis.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Hyper-Compression: Model Compression via Hyperfunction.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Gradient-Refined Federated Learning on Head-Tail Imbalanced Data.

IEEE transactions on neural networks and learning systems·2026

Same author

Frequency-spatial synergistic network for accelerated multi-contrast MRI reconstruction.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025

Same author

Boosting Geometric Invariants for Discriminative Forensics of Large-Scale Generated Visual Content.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Search research articles

相关实验视频

Updated: Jul 27, 2025

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

基于连续分解的Retinex图像增强,使用Plug-and-Play框架.

Tingting Wu, Wenna Wu, Ying Yang

IEEE transactions on neural networks and learning systems

|June 6, 2023

概括

这项研究介绍了一种基于Retinex的新框架,用于在低光下增强图像,同时消除噪音. 插即用 (plug-and-play) 模式提供了更好的解释性,并优于现有的方法.

科学领域:

计算机视觉计算机视觉
图像处理图像处理
人工智能的人工智能

背景情况:

雷提内克斯模型在低光条件下有效增强图像,但在噪音方面存在困难.
深度学习方法有前途,但需要大量的标记数据,缺乏可解释性.

研究的目的:

开发基于Retinex的框架,用于同时在低光下增强图像和消除噪音.
为了创建一个集成卷积神经网络 (CNN) 化器的插件运行模型.
为了提高模型的可解释性,以了解其行为.

主要方法:

使用了一种顺序的Retinex分解策略.
一个基于CNN的denoiser被集成到一个plug-and-play框架中,以生成一个反射功率组件.
最终的图像使用照明,反射率和马校正进行了增强.

主要成果:

拟议的框架有效地增强了低光图像,同时消除了噪音.
该框架在各种数据集中,与最先进的方法相比,表现优越.
该框架的插即用性质允许后期和临时解释性.

结论:

更多相关视频

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

相关实验视频

Last Updated: Jul 27, 2025

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

开发的框架提供了一个强大的解决方案,用于低光图像增强和denoising.
整合Retinex理论与CNNs提供了一个更易于解释和更有效的方法.
这种方法通过解决传统和基于深度学习的技术的局限性来推动该领域的发展.