Jove
Visualize
联系我们

相关概念视频

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

LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Interacted Planes Reveal 3D Line Mapping.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Rejoining fragmented ancient bamboo slips with physics-driven deep learning.

Nature communications·2026
Same author

Understanding Data Influence With Differential Approximation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
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

相关实验视频

Updated: Sep 18, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

高质量的伪标签用于点云细分,具有场景级注释.

Lunhao Duan, Shanshan Zhao, Xingxing Weng

    IEEE transactions on pattern analysis and machine intelligence
    |June 25, 2025
    PubMed
    概括
    此摘要是机器生成的。

    本研究引入了一种新的框架,用于生成高质量的伪标签,用于使用场景级注释进行室内点云语义细分. 它通过利用多模式信息和区域点语义一致性来提高准确性.

    更多相关视频

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.0K
    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

    相关实验视频

    Last Updated: Sep 18, 2025

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    9.1K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.0K
    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

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 3D数据处理 3D数据处理

    背景情况:

    • 室内点云的语义细分对于理解3D环境至关重要.
    • 场景级注释是一个重大挑战,因为缺乏精确的点级标签.
    • 现有的方法很难从场景级数据中生成准确的点级伪标签.

    研究的目的:

    • 提出一个高质量的伪标签生成框架,用于室内点云语义细分,使用场景级注释.
    • 通过解决当前伪标签技术的局限性,提高细分精度.
    • 改进点云数据中的特征学习和语义预测.

    主要方法:

    • 一个交叉模式的特征引导模块,利用2D-3D对应来对准点云和图像特征.
    • 一个区域点语义一致性模块,采用区域投票策略来指导点级预测.
    • 利用多模式信息和语义一致性来准确生成伪标签.

    主要成果:

    • 在场景级注释下,在ScanNet v2和S3DIS数据集上比以前的方法取得了显著的改进.
    • 证明了拟议框架在纠正不准确的点级语义预测方面的有效性.
    • 废弃性研究验证了该方法的各个组件的贡献.

    结论:

    • 拟议的框架有效地生成高质量的伪标签,用于室内点云语义细分和场景级注释.
    • 整合跨模式特征和区域点语义一致性显著提高了细分性能.
    • 这项工作为在3D语义细分任务中利用更少细粒度的注释提供了一个有希望的方向.