检索结果-南通市图书馆

Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

Computational Visual Media 2023年第2期9卷 229-247页

作者： Chun-Yu Sun Yu-Qi Yang Hao-Xiang Guo Peng-Shuai Wang Xin Tong Yang Liu Heung-Yeung Shum Institute for Advanced Study Tsinghua UniversityBeijing 100084China Microsoft Research Asia Beijing 100080China

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation *** propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D *** the unlabeled data,we present a novel multilevel consistency loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels:point level,part level,and hierarchical *** the labeled data,we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance *** method has been extensively validated on the task of 3D object semantic segmentation on PartNet and shapeNetPart,and indoor scene semantic segmentation on *** exhibits superior performance to existing semi-supervised and unsupervised pre-training 3D approaches.

关键词： shape segmentation semi-supervised learning multilevel consistency

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Improved quadric surfaces recognition from scanned mechanical models

引用

Computer Aided Drafting,Design and Manufacturing 2016年第4期26卷 9-19页

作者： Quan Weize Guo Jianwei Zhang Xiaopeng Yan Dongming National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China.

This paper presents a novel algorithm for identifying quadric surfaces from scanned mechanical models. We make several important improvements over the existing variational 3D shape segmentation framework, which utilizes Lloyd＇s iteration. First, instead of using randomized initialization （which likely falls into non-optimal minimum）, the RANSAC-based initialization approach is adopted. Given a good initialization, our method converges quickly than previous approaches. Second, in order to enhance the stability and the robustness, we carefully modify the distortion-minimizing flooding algorithm by using seed regions instead of seed triangles. Third, the geometric constraints are introduced into the optimization framework. The segmentation quality is further improved. We validate the efficiency and the robustness of our proposed method on various datasets, and demonstrate that our method outperforms state-of-art approaches.

关键词： shape segmentation quadric surfaces geometric constraints Lloyd's iteration

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：