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

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

Dark superabsorbers with a needle-like radiation.

Optics express·2026
Same author

Cusp solitons mediated by a topological nonlinearity.

Chaos (Woodbury, N.Y.)·2026
Same author

Improving NIR single-pixel imaging: using deep image prior and GANs.

Journal of the Optical Society of America. A, Optics, image science, and vision·2025
Same author

Bulk-Hole Correspondence and Inner Robust Boundary Modes in Singular Flatband Lattices.

Physical review letters·2025
Same author

Identifying topology of leaky photonic lattices with machine learning.

Nanophotonics (Berlin, Germany)·2024
Same author

Flat band fine-tuning and its photonic applications.

Nanophotonics (Berlin, Germany)·2024

相关实验视频

Updated: Jun 24, 2025

Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
06:45

Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

Published on: June 2, 2023

1.3K

Res-U2Net:未经训练的深度学习,用于相位检索和图像重建.

Carlos Osorio Quero, Daniel Leykam, Irving Rondon Ojeda

    Journal of the Optical Society of America. A, Optics, image science, and vision
    |June 10, 2024
    PubMed
    概括

    本研究引入了一个未经训练的Res-U2Net模型用于阶段检索,从而消除了对广泛训练数据的需求. 这种新的方法可以从相位信息中准确地进行3D表面重建.

    科学领域:

    • 光学和光子学 在光学和光子学.
    • 计算机视觉 计算机视觉
    • 3D成像是3D成像中的一种.

    背景情况:

    • 图像重建的深度学习通常需要大量的数据集,这些数据集通常是不切实际的.
    • 未经训练的深度学习方法通过学习在没有先前数据的情况下逆转物理图像形成过程来提供解决方案.
    • 阶段检索对于提取详细的对象信息至关重要,但传统方法面临数据限制.

    研究的目的:

    • 为阶段检索应用程序引入一种新的未经训练的深度学习模型Res-U2Net.
    • 利用提取的相位信息进行精确的表面变化检测和3D网格生成.
    • 评估Res-U2Net模型与现有的UNet和U2Net架构的性能.

    主要方法:

    • 开发一个未经训练的Res-U2Net深度学习架构,用于阶段检索.
    • 利用从模型中获得的相位信息来分析物体表面变化.
    • 生成一个网格表示来重建对象的3D结构.
    • 使用GDXRAY数据集进行比较分析,与UNet和U2Net模型进行比较.

    主要成果:

    • Res-U2Net模型证明了有效的阶段检索,而不需要大量的训练数据集.
    • 提取的相位信息准确地反映了物体表面的变化.

    更多相关视频

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
    06:25

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

    Published on: February 12, 2014

    8.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.7K

    相关实验视频

    Last Updated: Jun 24, 2025

    Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
    06:45

    Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

    Published on: June 2, 2023

    1.3K
    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
    06:25

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

    Published on: February 12, 2014

    8.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.7K
  • 从检索的相位数据成功生成3D网格表示.
  • 性能比较表明Res-U2Net在相位检索任务中的有效性.

    • 结论:

    • 拟议的未经训练的Res-U2Net模型是用于相位检索的可行和数据效率高的解决方案.
    • 这种方法有助于精确的3D表面重建和分析.
    • 这些发现表明,在数据稀缺的科学成像和计量学中,有可能有更广泛的应用.