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

Di-branched triphenylamine dye sensitized TiO<sub>2</sub> nanocomposites with good photo-stability for sensitive photoelectrochemical detection of organophosphate pesticides.

Analytica chimica acta·2018
Same author

pH-responsive gold nanoclusters-based nanoprobes for lung cancer targeted near-infrared fluorescence imaging and chemo-photodynamic therapy.

Acta biomaterialia·2018
Same author

[Ideas and methods on efficient screening of traditional medicines for anti-osteoporosis activity based on M-Act/Tox integrated evaluation using zebrafish].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2017
Same author

Ceftazidime-avibactam versus meropenem in nosocomial pneumonia, including ventilator-associated pneumonia (REPROVE): a randomised, double-blind, phase 3 non-inferiority trial.

The Lancet. Infectious diseases·2017
Same author

Myricetin against ischemic cerebral injury in rat middle cerebral artery occlusion model.

Molecular medicine reports·2017
Same author

Molecular Diversity Analysis and Genetic Mapping of Pod Shatter Resistance Loci in <i>Brassica carinata</i> L.

Frontiers in plant science·2017
Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
查看所有相关文章

相关实验视频

Updated: Jan 17, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

492

SPC:自主监督点云完成完成

Jie Song1, Xing Wu2, Junfeng Yao3

  • 1School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China.

Neural networks : the official journal of the International Neural Network Society
|September 18, 2025
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种自我监督的点云完成 (SPC) 方法,可以从部分数据中重建完整的3D形状,而不需要多个视图. 这种方法显著提高了准确性,并有助于下游任务,如分类.

关键词:
深度学习是一种深度学习.完成点云完成点云.这是真实的扫描.自主监督学习学习

更多相关视频

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.4K
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

3.3K

相关实验视频

Last Updated: Jan 17, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

492
Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

1.4K
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

3.3K

科学领域:

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

背景情况:

  • 来自深度传感器的点云往往缺乏完整的形状信息.
  • 现有的完成方法需要广泛的训练数据 (完整的点云或多视图图像),限制了现实世界的适用性.
  • 高昂的信息获取成本阻碍了现有点云完成技术的实际部署.

研究的目的:

  • 开发一种自我监督的点云完成 (SPC) 方法.
  • 为了使点云完成,只使用单个部分点云进行培训.
  • 克服依赖于完整数据或多视图信息的现有方法的局限性.

主要方法:

  • 开发了一种类似自动编码器的网络架构,采用两步策略.
  • 为了学习完整的点云表示,采用了压缩重建策略.
  • 引入了一项全球增强战略,以防止过度装配,并保持预测点的位置连贯性.

主要成果:

  • 拟议的SPC方法表明,在现实数据集上,单向Chamfer距离 (UCD) 和单向Hausdorff距离 (UHD) 的平均值分别减少了2.3和2.4.
  • 与最先进的方法相比,该方法取得了显著的改进.
  • 应用SPC提高了点云分类准确度,平均提高了14%.

结论:

  • 开发的自主监督点云完成方法为从不完整的数据中重建完整的3D形状提供了实用解决方案.
  • 该方法有效地从单个部分点云中学习,减少对昂贵数据采集的依赖.
  • 该方法具有很高的实用价值,提高了点云完成和下游任务性能.