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

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

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...

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

Two-year-supervised resistance training prevented diabetes incidence in people with prediabetes: A randomised control trial.

Diabetes/metabolism research and reviews·2019

Same author

Preliminary evaluation of a predictive controller for a rotary blood pump based on pulmonary oxygen gas exchange.

Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine·2019

Same author

A Destructive New Disease of Citrus in China Caused by Cryptosporiopsis citricarpa sp. nov.

Plant disease·2019

Same author

Effects of membrane reference state on shape memory of a red blood cell.

Computer methods in biomechanics and biomedical engineering·2019

Same author

Ultrafast Photovoltaic-Type Deep Ultraviolet Photodetectors Using Hybrid Zero-/Two-Dimensional Heterojunctions.

ACS applied materials & interfaces·2019

Same author

Phenolic profile and antioxidant properties of sand rice (Agriophyllum squarrosum) as affected by cooking and in vitro digestion.

Journal of the science of food and agriculture·2019

Search research articles

相关实验视频

Updated: Jun 2, 2025

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

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

Published on: December 15, 2023

功能增强的级联注意力网络,用于轻量级图像超分辨率.

Feng Huang¹, Hongwei Liu¹, Liqiong Chen¹

¹College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350108, China.

Scientific reports

|January 15, 2025

概括

我们开发了一个功能增强级联注意网络 (FECAN),以实现高效的图像超分辨率 (SR). FECAN提高了视觉质量,降低了计算成本,优于其他轻型SR模型.

关键词:

卷积神经网络是一个卷积神经网络.增强的混合注意力注意力.轻量级图像超分辨率超级分辨率多尺度大可分离内核的注意力

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Super-resolution Imaging of Neuronal Dense-core Vesicles

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

相关实验视频

Last Updated: Jun 2, 2025

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

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

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Super-resolution Imaging of Neuronal Dense-core Vesicles

Super-resolution Imaging of Neuronal Dense-core Vesicles

Published on: July 2, 2014

科学领域:

计算机视觉计算机视觉
深度学习 (Deep Learning) 是一种深度学习.
图像处理图像处理

背景情况:

注意力机制通过捕捉特征依赖性来增强图像恢复.
现有的方法在感知能力和低功耗设备的效率方面存在局限性.

研究的目的:

提出一个新的功能增强级联注意网络 (FECAN),以实现高效和高性能的图像超分辨率 (SR).
解决当前注意力机制在感知质量和计算成本方面的局限性.

主要方法:

引入了一个功能增强级联注意力 (FECA) 机制,包括增强混合注意力 (ESA) 和多尺度大可分离内核注意力 (MLSKA).
欧空局 (ESA) 增强了高频纹理特征,而MLSKA则进一步提取和融合了多层次信息.
通过在网络内变化高频增强模块 (HFEM) 的数量来评估FECAN的有效性.

主要成果:

在客观指标和主观视觉质量方面,FECAN在最先进的轻型SR网络上表现优越.
在121K模型尺寸的4x尺度上,FECAN比MAN-tiny.取得了0.07dB的PSNR改进.
与MAN-tiny.com相比,FECAN减少了约19%的网络参数和约20%的FLOP.

结论:

在超分辨率性能和模型复杂性之间,FECAN提供了更好的权衡.
拟议的FECA机制有效地提取和融合丰富,细粒度的高频信息,以增强SR.
FECAN适用于需要高质量的图像恢复的低功耗设备.