Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Light Acquisition02:16

Light Acquisition

8.0K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.0K

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

Early Anterior Cruciate Ligament Reconstruction Reduces Long-Term Rates of Secondary Meniscus Surgery: A Systematic Review.

Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association·2026
Same author

Integrated analysis of single-cell and bulk-RNA sequencing data reveals drug therapeutic targets and prognostic biomarkers related to ribosome biogenesis in hepatocellular carcinoma.

Pakistan journal of pharmaceutical sciences·2026
Same author

Polyphenols-based functional nanomaterial systems for the treatment of periodontitis.

Biomaterials advances·2026
Same author

DMM-UNet: dual-path multi-scale Mamba UNet for medical image segmentation.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Cyclic Heptapeptide FZ1 Acts as an Integrin αvβ3 Agonist to Facilitate Diabetic Skin Wound Healing by Enhancing Angiogenesis.

Journal of medicinal chemistry·2025
Same author

Infrared and Visible Image Fusion via Residual Interactive Transformer and Cross-Attention Fusion.

Sensors (Basel, Switzerland)·2025

相关实验视频

Updated: May 3, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

使用生成对抗网络进行低光图像增强.

Litian Wang1, Liquan Zhao2, Tie Zhong1

  • 1Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology(Ministry of Education), Northeast Electric Power University, Jilin, 132012, China.

Scientific reports
|August 9, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了一个生成对抗网络,以增强低光照明图像. 该方法提高了亮度,颜色和细节,在合成和现实世界低光图像上表现优于现有技术.

关键词:
生成性的对抗性网络.照明注意力模块照明注意力模块多级特征提取模块多级特征提取模块夜间道路场景图像增强 图像增强

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

499
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.0K

相关实验视频

Last Updated: May 3, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

499
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.0K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 图像处理 图像处理

背景情况:

  • 低光条件降低图像亮度,掩盖细节并阻碍图像分析.
  • 现有的低光图像增强方法难以有效地恢复颜色和细节.

研究的目的:

  • 开发一个先进的生成对抗网络 (GAN) 以实现优越的低光图像增强.
  • 为了提高低光环境下拍摄的图像的亮度,颜色保真度和细节保存.

主要方法:

  • 一个包含多尺度特征提取和照明注意模块的生成网络.
  • 在生成网络中的编码器-解码器架构,用于增强功能处理.
  • 一个双重歧视的对抗网络 (全球和本地) 来改进图像生成.
  • 一个改进的损失功能,结合颜色和感知损失,以最大限度地减少颜色扭曲.

主要成果:

  • 拟议的GAN取得的结果接近于合成低光数据的正常照明图像.
  • 与其他方法相比,增强的真实低光图像显示出优越的细节保留和清晰度.
  • 量化绩效指标表明,拟议的增强技术的整体有效性更高.

结论:

  • 开发的生成对抗网络在低光条件下显著改善了图像增强.
  • 该方法有效地解决了亮度,颜色和细节恢复方面的挑战.
  • 它在合成和现实世界低光图像数据集上都表现出强的性能.