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

Deconvolution01:20

Deconvolution

519
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
519
Reducing Line Loss01:18

Reducing Line Loss

337
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...
337
Convolution Properties II01:17

Convolution Properties II

547
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
547
Downsampling01:20

Downsampling

568
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
568

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

Abiotic Peptide-Like Bond Formation in Gas-Phase Nitrile-Water Clusters Driven by Vacuum Ultraviolet Photoionization.

Journal of the American Chemical Society·2026
Same author

Biosynthetic composite iron minerals enhance electroactive biofilm activity and stability by reducing charge transfer resistance and buffering the internal acid inhibition.

Bioresource technology·2026
Same author

Genomic distribution characteristics and interspecific differences of microsatellite landscapes in Felidae.

BMC genomics·2026
Same author

Endoscopic Submucosal Dissection for Gastritis Cystica Profunda Mimicking a Gastric Submucosal Tumour.

ANZ journal of surgery·2026
Same author

Reactive Dissolution-Thermal Conversion Enables Closed-Pore Filling in Hard Carbon toward Potassium Storage.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Broadband reflective wavefront manipulation enabled by a polarization-twisting design method.

Optics express·2026

相关实验视频

Updated: Jan 6, 2026

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

987

使用动态卷积神经网络的轻量级自适应图像消除模糊框架.

Xianqiu Zheng1,2, Yujian Li3,4, Yujie Zhu4

  • 1School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, 541004, China. 2267555949@qq.com.

Scientific reports
|September 26, 2025
PubMed
概括

本研究介绍了一种使用动态卷积神经网络的轻量级自适应图像消除模糊框架. 该模型提高了适应性和全球上下文建模,以获得更清晰的图像和较低的计算成本.

关键词:
动态卷积神经网络 动态卷积神经网络图像消除模糊的方法轻量级的适应性框架 轻量级的适应性框架在MAF中,MAF是MAF.这是SAFM的SAFM.这就是SSA SSA.

相关实验视频

Last Updated: Jan 6, 2026

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

987

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:

  • 图像消除模糊在计算机视觉中至关重要.
  • 轻量级模型在适应性和全球背景方面扎.
  • 现有的方法往往缺乏实际应用的效率.

研究的目的:

  • 提出一个新的轻量级自适应图像消除模糊的框架.
  • 为了提高适应各种模糊模式的适应性.
  • 改进全球上下文建模和多尺度特征融合.

主要方法:

  • 开发了一个使用动态卷积神经网络的框架.
  • 引入了浅度适应特征模块 (SAFM),用于输入特定的内核调整.
  • 集成的注意力特征调节模块 (AFCM) 与简单的空间注意力 (SSA) 适用于全球环境.
  • 利用多尺度注意力融合 (MAF) 进行层次特征聚合.

主要成果:

  • 实现了具有竞争力的峰值信号噪声比 (PSNR) 和结构相似度指数 (SSIM) 的表现.
  • 在GoPro和HIDE数据集上证明了有效性.
  • 与其他轻量级模型相比,保持了相对较低的计算复杂性.

结论:

  • 拟议的轻量级自适应框架有效地解决了图像消除模糊性的挑战.
  • 为需要高效消除模糊的智能应用提供实用解决方案.
  • 动态卷曲和注意力机制提高了适应能力和上下文建模.