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

601
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.
601

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

Primary pulmonary NFATC2::NUTM2-associated myoepithelial-like neoplasms: two hi-C-detected cases beyond routine targeted NGS and review of the literature.

Virchows Archiv : an international journal of pathology·2026
Same author

Development of an integrated multidimensional nomogram for predicting stone-free status after retrograde intrarenal surgery: a machine learning-based approach.

Minerva urology and nephrology·2026
Same author

Machine learning prediction of overall survival in patients with cT1b renal cell carcinoma after surgical resection using the SEER database.

Scientific reports·2025
Same author

Real-world safety assessment of tamsulosin based on adverse event analysis from the FAERS database.

Scientific reports·2025
Same author

U-shaped association between ultra-processed food intake and overactive bladder in US adults: a national cross-sectional study.

Frontiers in nutrition·2025
Same author

Association between oral microbiome diversity and kidney stones: a cross-sectional study.

Frontiers in microbiology·2025

相关实验视频

Updated: Jun 10, 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

478

一个基于变压器的图像引导深度完成模型与双重注意力融合模块.

Shuling Wang1, Fengze Jiang1, Xiaojin Gong1

  • 1The College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China.

Sensors (Basel, Switzerland)
|October 16, 2024
PubMed
概括

这项研究介绍了一种基于变压器的新型网络,用于图像引导的深度完成,通过从稀疏的输入生成准确的,密集的深度地图来显著改善3D场景感知.

科学领域:

  • 计算机视觉 计算机视觉
  • 3D场景感知 3D场景感知
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 深度信息对于理解3D场景至关重要,但直接传感器捕获会产生不完整和杂的深度图.
  • 图像引导的深度完成旨在通过使用彩色图像从稀疏的深度数据生成密集,准确的深度图.

研究的目的:

  • 开发一种新的网络架构,用于准确和高分辨率的图像引导深度完成.
  • 利用变压器模型和注意力机制来增强深度地图生成.

主要方法:

  • 一个双分支网络架构,利用基于变压器的编码器进行特征提取.
  • 将图像特征序列化为令牌,并提取多层次金字塔特征.
  • 一个双注意力融合模块,结合空间,通道和交叉注意力机制来实现特征融合.

主要成果:

  • 拟议的模型在NYUv2和SUN-RGBD深度数据集上实现了最先进的性能.
  • 废弃性研究验证了个别网络模块的有效性.
  • 该方法成功地从稀疏的输入中生成密集和准确的深度图.

结论:

  • 变压器模型对于图像引导的深度完成任务非常有效.
关键词:
在深度完成完成.双重注意力的融合模块多尺度双分支的双分支公司.

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376

相关实验视频

Last Updated: Jun 10, 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

478
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376
  • 拟议的双注意力融合模块显著提高了色彩和深度信息之间的功能融合.
  • 新的网络架构提供了一个强大的解决方案,通过深度完成来改善3D场景的感知.