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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

7.7K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
7.7K

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

Porous CaP/silk composite scaffolds to repair femur defects in an osteoporotic model.

Journal of materials science. Materials in medicine·2013
Same author

Increased proliferation of human bladder smooth muscle cells is mediated by physiological cyclic stretch via the PI3K‑SGK1‑Kv1.3 pathway.

Molecular medicine reports·2013
Same author

Preparation and evaluation of charged solid lipid nanoparticles of tetrandrine for ocular drug delivery system: pharmacokinetics, cytotoxicity and cellular uptake studies.

Drug development and industrial pharmacy·2013
Same author

MicroRNA-19a targets tissue factor to inhibit colon cancer cells migration and invasion.

Molecular and cellular biochemistry·2013
Same author

Identification and validation of risk factors for postoperative infectious complications following hepatectomy.

Journal of gastrointestinal surgery : official journal of the Society for Surgery of the Alimentary Tract·2013
Same author

Osteopenia predicts curve progression of adolescent idiopathic scoliosis in girls treated with brace treatment.

Journal of pediatric orthopedics·2013

相关实验视频

Updated: Sep 15, 2025

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution
08:41

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution

Published on: August 16, 2012

11.6K

一个轻量级的高频mamba网络用于图像超分辨率.

Tao Wu1, Wei Xu2, Yajuan Wu3

  • 1School of Electronic Information Engineering, China West Normal University, Si'chuan, Nanchong, 637009, China.

Scientific reports
|July 17, 2025
PubMed
概括

本研究介绍了用于单图像超分辨率 (SISR) 的高频曼巴网络 (HFMN). 使用VMamba,HFMN有效地集成本地和全球图像功能,以更少的参数实现最先进的结果.

关键词:
双分支的融合是双分支的融合.图像超分辨率的超级分辨率互动注意力 互动注意力视觉的曼巴 视觉的曼巴

更多相关视频

Super-resolution Imaging of Neuronal Dense-core Vesicles
09:30

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

9.8K
Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons
14:02

Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons

Published on: October 31, 2020

5.9K

相关实验视频

Last Updated: Sep 15, 2025

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution
08:41

Lensfree On-chip Tomographic Microscopy Employing Multi-angle Illumination and Pixel Super-resolution

Published on: August 16, 2012

11.6K
Super-resolution Imaging of Neuronal Dense-core Vesicles
09:30

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

9.8K
Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons
14:02

Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons

Published on: October 31, 2020

5.9K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 单图像超分辨率 (SISR) 研究重点是提高图像分辨率.
  • 现有的方法往往难以有效地结合本地和全球图像信息.
  • 卷积神经网络 (CNN) 和变压器是常见的,但在整合各种信息类型方面存在局限性.

研究的目的:

  • 为SISR开发一种新的方法,优化整合本地和全球图像特征.
  • 解决SISR中基于变压器的模型所带来的计算复杂性.
  • 提出一个轻量级但有效的网络,以超高分辨率进行高频细节恢复.

主要方法:

  • 为SISR提出了高频Mamba网络 (HFMN).
  • 利用自我注意力机制来平衡本地和全球信息权重.
  • 采用选择性状态空间模型VMamba,以高效地提取全局特征,降低计算复杂性.
  • 引入了专门的模块:局部高频特征区块 (LHFB),基于Mamba的注意区块 (MAB) 和双信息交互式注意区块 (DIAB).

主要成果:

  • 与最近的最先进的 (SOTA) 方法相比,HFMN在基准SISR数据集上表现优越.
  • 拟议的网络有效地实现了高频细节恢复.
  • HFMN以显著更少的参数实现了这些结果,这表明了轻量级的架构.

结论:

  • 通过使用VMamba和注意力机制,HFMN有效地整合了SISR的本地和全球信息.
  • 该网络为超分辨率任务提供了计算效率高,重量轻的解决方案.
  • HFMN代表了SISR的重大进步,以提高效率优于现有方法.