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

Wide-Field Oxygen Permeability Measurement of Contact Lenses Using a Modified Polarographic Electrode Cell.

Sensors (Basel, Switzerland)·2026
Same author

Various Antihypertensive Drug Compliance Models and Cardiovascular Prognosis of People With Incidentally Detected High Blood Pressure During Health Check-Up in Korea.

International journal of hypertension·2026
Same author

Poor cardiovascular outcomes of underweight abdominal obesity in the entire population of newly diagnosed heart failure.

ESC heart failure·2025
Same author

Evaluation of Optical and Thermal Properties of NIR-Blocking Ophthalmic Lenses Under Controlled Conditions.

Sensors (Basel, Switzerland)·2025
Same author

Obesity Report: Distribution and Pattern by Age and Sex in Heart Failure Cohort over 10 Years in Korea.

Journal of cardiovascular development and disease·2025
Same author

Lipid-Lowering Effect and Safety of Ezetimibe and Atorvastatin 5 mg in Patients With Primary Hypercholesterolemia or Mixed Dyslipidemia: A Randomized, Double-Blind, Parallel, Multicenter, Phase 3 Clinical Trial.

Clinical cardiology·2025

相关实验视频

Updated: Jul 2, 2025

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

一种新的方法,用于单眼深度估计,使用沙表部模块.

Seung-Jin Oh1, Seung-Ho Lee1

  • 1Department of Electronic Engineering, Hanbat National University, 125, Dongseo-daero, Yuseong-gu, Daejeon 34158, Republic of Korea.

Sensors (Basel, Switzerland)
|February 24, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种新的单眼深度估计方法,使用沙钟部模块和Swin Transformer V2. 这种新的方法实现了卓越的准确性,超过了生成深度图像的现有技术.

关键词:
可变形的注意力注意力沙钟模块的部模块是什么蒙面图像建模模的模拟图像单眼的深度估计估计.斯温变压器 V2 的变压器 V2 的变压器

更多相关视频

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
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

783

相关实验视频

Last Updated: Jul 2, 2025

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
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
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

783

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.

背景情况:

  • 单眼深度估计对于场景理解至关重要.
  • 现有的方法在准确捕捉本地和全球特征方面面临挑战.

研究的目的:

  • 提出一种新的单眼深度估计方法.
  • 使用先进的深度学习架构,提高深度预测的准确性和效率.

主要方法:

  • 使用Swin Transformer V2与蒙面图像建模 (MIM) 进行特征提取.
  • 采用一个沙钟部模块来保存特征地图属性.
  • 整合可变形的注意力来降低计算成本并增强局部性.
  • 具有解卷和上抽样层的解码器生成最终的深度图.

主要成果:

  • 拟议的方法在纽约大学深度V2数据集上实现了0.274的根平均平方误差 (RMSE).
  • 这一RMSE值低于以前发表的方法报告的值.
  • 在单眼深度估计准确度方面表现卓越.

结论:

  • 这种新的方法有效地从单个图像中估计了深度.
  • 斯温变压器V2和沙钟部模块的集成证明是有利的.
  • 该方法为单眼深度估计提供了更有效,更准确的解决方案.