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

651
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.
651

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

Modeling and decoupling phase-shift-induced wavefront distortion in high NA spherical Fizeau interferometry via aberration-related iterative algorithm.

Optics express·2026
Same author

Machine learning-assisted nanozyme nanosensor for instantaneous quantitative analysis of antitubercular drugs.

Journal of nanobiotechnology·2026
Same author

Clinical characteristics and <i>ompA</i> serovar correlation in adult inclusion conjunctivitis: a cohort study in China.

The British journal of ophthalmology·2026
Same author

Advances in alginate-based hydrogel wound dressings: Composite strategies, application type, and multifunctional therapeutics: A review.

International journal of biological macromolecules·2026
Same author

Phenolic Copigment Enhanced Anthocyanin Stability and Color Intensity of Frozen Red Huajiao (<i>Zanthoxylum bungeanum</i> Maxim.) Fruit.

Foods (Basel, Switzerland)·2026
Same author

Application of Ultrasonication as an Emerging Non-Thermal Physical Technology in Meat Product Processing: A Review.

Foods (Basel, Switzerland)·2026

相关实验视频

Updated: Jul 1, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.0K

AMENet是一个单眼深度估计网络,专为自动立体显示设计.

Tianzhao Wu1,2, Zhongyi Xia1,2, Man Zhou1,2

  • 1College of New Materials and New Energies, Shenzhen University of Technology, Shenzhen, 518118, Guangdong, China.

Scientific reports
|March 12, 2024
PubMed
概括

本研究介绍了AMENet,这是一个融合视觉变换器 (ViT) 和卷积神经网络 (CNN) 的新型网络,用于增强单眼深度估计. 在复杂的场景中,AMENet 提高了对自动立体镜显示器的精度和稳定性.

关键词:
在美国,CNN是CNN.失去了深度的损失.单眼深度估计的估计方法变压器变压器变压器

更多相关视频

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

4.5K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.4K

相关实验视频

Last Updated: Jul 1, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.0K
Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

4.5K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.4K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 单眼深度估计对于自动立体镜显示器至关重要,但在复杂环境中在准确性和稳定性方面面临挑战.
  • 现有的方法很难在各种复杂的视觉场景中实现可靠的性能.

研究的目的:

  • 开发一个先进的深度估计网络,AMENet,集成视觉转换器 (ViT) 和卷积神经网络 (CNN) 架构.
  • 提高单眼深度估计的准确性和稳定性,特别是用于自立体显示器的应用.

主要方法:

  • 拟议的AMENet融合了ViT用于全球语义特征提取和CNN用于详细特征处理.
  • 整合了一个重量校正模块,以量化损失关系并增强模型的稳定性.
  • 输入图像被处理为视觉特征的序列,以利用ViT的全球感知能力.

主要成果:

  • 与多个公共数据集的现有方法相比,AMENet的准确性和稳定性更高.
  • 与基线相比,该网络在KITTI数据集上取得了显著的4.4%的准确性改进.
  • 实验分析证实了该方法在各种场景和复杂条件下的有效性和稳定性.

结论:

  • AMENet在单眼深度估计方面取得了重大进展,提供了高精度和稳定性.
  • ViT和CNN架构的融合为应对复杂的深度估计挑战提供了一个强大的方法.
  • 拟议的方法非常适合要求高的应用,如自动立体显示器.