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

Mycoelectronics: Bioprinted living fungal bioelectronics for artificial sensation.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

X-ray-activated NaLu/GdF<sub>4</sub>:Tb<sup>3+</sup> persistent luminescence nanocarrier for synergistic radiotherapy and sustained photodynamic/chemotherapy of Cancer.

Journal of colloid and interface science·2026

Same author

Early postnatal antibiotic-associated gut microbiota alterations might promote long-term lipid metabolism via brown adipose tissue metabolic programming.

Gut microbes·2026

Same author

Predictive Value of Nutritional Status in Sputum Culture Conversion Among Patients with Nontuberculous Mycobacterial Pulmonary Disease: A Retrospective Cohort Study.

Infection and drug resistance·2026

Same author

Multidimensional Engineering of Single-Atom Iron Nanozymes for Machine Learning-Assisted Multiplexed Sensing.

Analytical chemistry·2026

Same author

Soft Supervision Guided Spatial-Temporal Refinement Network For Video-based Visible-Infrared Person Re-Identification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Search research articles

相关实验视频

Updated: Jun 21, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

通过位置注意网络实现全向图像超分辨率.

Xin Wang¹, Shiqi Wang², Jinxing Li³

¹School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, 518055, China; Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology, Shenzhen, Shenzhen, 518055, China; Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong.

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

|July 5, 2024

概括

这项研究引入了一种新的位置注意网络 (PAN),以提高全向图像超分辨率 (ODISR). PAN有效地解决了等直角投影图像中的几何扭曲,以增强视觉体验.

关键词:

扭曲的特征是扭曲的特征.一个全方位的图像.位置注意力位置注意力超级分辨率的超级分辨率

更多相关视频

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

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

相关实验视频

Last Updated: Jun 21, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

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:

在等直角投影 (ERP) 中的全向图像 (ODIs) 的分辨率较低,并且遭受显著的几何扭曲和像素拉伸,特别是在更高的度.
由于这些扭曲,传统的超分辨率 (SR) 方法与ERP ODI扎,导致低于最佳的全向图像超分辨率 (ODISR) 性能.
更好的沉浸式体验需要有效的ODISR技术,这些技术可以应对ERP格式的独特挑战.

研究的目的:

提出一种新的位置注意网络 (PAN),专门设计用于全向图像超分辨率 (ODISR).
为应对ERP ODI中的几何扭曲和像素拉伸所带来的挑战.
为了提高ODISR的性能,超越传统的SR方法.

主要方法:

引入了两个分支网络:一个基本增强 (BE) 分支用于粗特征增强和一个位置注意力增强 (PAE) 分支.
该PAE分支利用位置注意力机制,根据度和拉伸度动态调整特征贡献,增强相关信息并抑制冗余.
集成了一个长期存储器 (LM) 模块,用于改进特征融合,扭曲感知和对等级特征的聚合.

主要成果:

拟议的PAN有效地通过根据空间扭曲动态调节贡献来增强特征.
在BE和PAE分支之间的特征融合完善了图像,并适应了ODI扭曲特征.
广泛的实验表明,PAN在ODISR中实现了最先进的性能和高效率.

结论:

新的位置注意网络 (PAN) 通过解决ERP扭曲,显著提高了全向图像超分辨率 (ODISR).
集成的定位注意力和长期记忆模块是增强特征差异化和空间扭曲适应的关键.
PAN为实现高质量的ODISR提供了高效和有效的解决方案.