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

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

Case Report: First occurrence of smoldering multiple myeloma in activated phosphoinositide 3-Kinase δ syndrome.

Frontiers in oncology·2026
Same author

Effect of Pore Structure Parameters on Thermal Insulation Performance of Porous Ceramics Fabricated by Material Jetting.

Materials (Basel, Switzerland)·2026
Same author

Research Progress on Preparation Technology, Structure Optimization and Properties of 3D-Printed Porous Ceramics.

Materials (Basel, Switzerland)·2026
Same author

Infrared radiation-assisted drying stabilizes rice flavor by modulating volatile composition and lipid metabolism.

Food chemistry·2026
Same author

Metagenomic profiling of biliary microbiota reveals distinct microbial and functional features in cholelithiasis and cholecystic polyps.

Medicine·2026
Same author

Size-Dependent Mechanical Properties of Additively Manufactured Ti-6Al-4V Thin Walls.

Materials (Basel, Switzerland)·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
查看所有相关文章

相关实验视频

Updated: Jan 7, 2026

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.4K

扩散驱动的自我监督学习用于形状重建和姿势估计.

Jingtao Sun, Yaonan Wang, Mingtao Feng

    IEEE transactions on pattern analysis and machine intelligence
    |December 24, 2025
    PubMed
    概括
    此摘要是机器生成的。

    本研究介绍了一种新的扩散驱动的自我监督网络,用于类别级的姿势估计和形状重建. 该方法有效地处理多对象场景,并且优于没有手动标签的现有方法.

    更多相关视频

    Three-Dimensional Shape Modeling and Analysis of Brain Structures
    05:33

    Three-Dimensional Shape Modeling and Analysis of Brain Structures

    Published on: November 14, 2019

    7.6K
    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
    12:06

    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

    Published on: March 3, 2023

    4.6K

    相关实验视频

    Last Updated: Jan 7, 2026

    Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
    09:27

    Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

    Published on: January 30, 2019

    7.4K
    Three-Dimensional Shape Modeling and Analysis of Brain Structures
    05:33

    Three-Dimensional Shape Modeling and Analysis of Brain Structures

    Published on: November 14, 2019

    7.6K
    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
    12:06

    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

    Published on: March 3, 2023

    4.6K

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 机器人技术 机器人技术 机器人技术

    背景情况:

    • 完全监督的类别级姿势估计需要昂贵的手动注释.
    • 现有的自我监督方法通常依赖于合成数据或CAD模型,并且仅限于单个对象.
    • 多个对象的姿势估计和形状重建仍然是具有挑战性的任务.

    研究的目的:

    • 开发一个以扩散驱动的自我监督网络,用于多对象形状重建和类别级别的姿势估计.
    • 通过利用没有合成数据或CAD模型的形状先验来克服现有方法的局限性.
    • 为了应对课内形状变化的挑战,并提高复杂场景的性能.

    主要方法:

    • 引入了用于SE(3) 等价姿势特征和3D尺度不变形状信息的先前知晓的金字塔3D点变压器.
    • 利用点卷积层与辐射核用于姿势意识学习和图形卷积用于形状表示.
    • 开发了一种包含扩散机制的预训练至精炼自主监督训练范式.

    主要成果:

    • 拟议的网络在自主监督的类别级定位估计中取得了最先进的性能.
    • 在多个公共数据集和自定义数据集上表现优于现有的自我监督方法.
    • 在多对象场景和形状重建任务中表现出有效性,超过了一些完全监督的方法.

    结论:

    • 扩散驱动的自我监督网络为类别级的姿势估计和形状重建提供了强大的解决方案.
    • 该方法有效地利用形状先验并处理类内变化,减少对手册注释的依赖.
    • 这种方法推进了计算机视觉中的自我监督学习,用于复杂的3D场景理解.