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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

700
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
700
Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

7.0K
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...
7.0K
Deconvolution01:20

Deconvolution

180
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...
180
Upsampling01:22

Upsampling

254
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
254

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

Intelligent quantification of Mn(VII) using a YOLO v3 artificial intelligence-driven smartphone monitoring platform based on nitrogen-doped blue fluorescence carbon dots.

The Analyst·2026
Same author

Mechanism of ferroptosis in progressive injury of skeletal muscle caused by high-voltage electrical burns and the intervention effect of uAMC3203.

Burns : journal of the International Society for Burn Injuries·2026
Same author

Pectin biosynthesis, signaling, and cell polarity in stomatal function and morphogenesis.

Current opinion in plant biology·2026
Same author

A multifunctional nanotherapeutic strategy based on exosome-liposome hybrid nanoparticles for comprehensive periodontitis management.

Journal of nanobiotechnology·2026
Same author

3D Fibrin/Gelatin Hydrogel System Enhances the Therapeutic Potency of DPSC-Derived Extracellular Vesicles Compared to 2D Culture in Accelerating Diabetic Wound Healing via Angiogenesis and Immune Modulation.

Journal of functional biomaterials·2026
Same author

PyCaspase-3 mediates haemocyte apoptosis in the Yesso scallop (Patinopecten yessoensis) in response to high temperature stress.

Fish & shellfish immunology·2026
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
查看所有相关文章

相关实验视频

Updated: Jul 15, 2025

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

568

自主监督的深度超分辨率与对比的多视图预训练.

Xin Qiao1, Chenyang Ge1, Chaoqiang Zhao2

  • 1Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, 710049, China.

Neural networks : the official journal of the International Neural Network Society
|September 28, 2023
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种自我监督的深度超分辨率方法,使用对比的多视图预训练. 它有效地取样了没有配对数据的深度地图,优于现有的深度超分辨率技术.

关键词:
具有对比性的预训练.跨模式的交叉方式.深度超分辨率超级分辨率相互调节的相互调节自主监督学习学习

更多相关视频

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439

相关实验视频

Last Updated: Jul 15, 2025

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

568
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 像指导深度超分辨率 (GDSR) 这样的低水平视觉任务面临挑战,因为配对训练数据有限.
  • 自主监督学习提供了一个解决方案,但在没有高分辨率目标的情况下提取深度图仍然很困难.

研究的目的:

  • 提出一种新的自我监督的深度超分辨率方法.
  • 为了应对GDSR中不足的配对培训数据的挑战.
  • 为了提高深度地图上采样的准确性和概括性.

主要方法:

  • 一种自我监督的深度超分辨率方法,利用对比的多视图预训练.
  • 一种可适应回归任务的策略,即使是小数据集,通过提取独特的指导特征来减少信息冗余.
  • 一个新的相互调制方案,用于计算跨模态特征之间的局部空间相关性.

主要成果:

  • 与最先进的GDSR技术相比,提出的方法实现了更高的性能.
  • 在没有明确的高分辨率监督的情况下,展示了有效的深度地图上采样.
  • 在不同的模式中表现出良好的概括能力.

结论:

  • 开发的自我监督方法有效地克服了GDSR.中的数据限制.
  • 对比的多视图预训练和相互调制方案增强了特征提取和空间相关性.
  • 该方法显示了在推进自主监督深度估计和相关视觉任务方面具有重大潜力.