相关实验视频

Updated: Jan 10, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

弱监督的形状通过结构分解完成点云的多重完成

Changfeng Ma, Pengxiao Guo, Shuangyu Yang

IEEE transactions on visualization and computer graphics

|November 24, 2025

概括

这项研究引入了一种新的弱监督方法,用于使用结构分解完成3D形状,改进从没有签名距离函数 (SDF) 的部分点云生成网格. 这种方法提高了现实数据的稳定性和准确性.

科学领域:

计算机视觉计算机视觉
三维重建的3D重建
几何深度学习几何深度学习

背景情况:

部分点云对于完全的3D网格生成具有重大挑战.
现有的方法在数据可访问性,形状保存和实时扫描数据的稳定性方面扎.
在训练期间经常需要签名距离函数 (SDF),限制灵活性.

研究的目的:

为3D网格开发一种创新的低监督形状完成方法.
通过利用结构信息来克服当前方法的局限性.
为了消除在训练期间对SDF的需求.

主要方法:

使用结构分解的弱监督的形状完成方法.
将对象表示为抽象的结构框架和部分细节.
利用基于图像的零件细节的完成网络和基于扩散的网络来生成多个结果.

主要成果:

在3D形状完成方面实现了最先进的 (SOTA) 性能.
与以前的方法相比,显示了超过38.1%的平均改善.
在人工和真实扫描数据集上展示了卓越的稳定性和准确性.

结论:

提出的方法有效地从部分点云生成完整的3D网格.
通过结构性分解进行弱监督的学习为基于SDF的培训提供了强大的替代方案.
这种方法显著推进了3D形状完成领域.

更多相关视频

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

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

Published on: April 18, 2025

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring

Published on: June 13, 2025

相关概念视频

Structural Classification of Joints

Structural Classification of Joints

Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...