当前位置: X-MOL 学术ACM Trans. Graph. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Unsupervised Detection of Distinctive Regions on 3D Shapes
ACM Transactions on Graphics  ( IF 6.2 ) Pub Date : 2020-06-01 , DOI: 10.1145/3366785
Xianzhi Li 1 , Lequan Yu 1 , Chi-Wing Fu 1 , Daniel Cohen-Or 2 , Pheng-Ann Heng 1
Affiliation  

This article presents a novel approach to learn and detect distinctive regions on 3D shapes. Unlike previous works, which require labeled data, our method is unsupervised. We conduct the analysis on point sets sampled from 3D shapes, then formulate and train a deep neural network for an unsupervised shape clustering task to learn local and global features for distinguishing shapes with respect to a given shape set. To drive the network to learn in an unsupervised manner, we design a clustering-based nonparametric softmax classifier with an iterative re-clustering of shapes, and an adapted contrastive loss for enhancing the feature embedding quality and stabilizing the learning process. By then, we encourage the network to learn the point distinctiveness on the input shapes. We extensively evaluate various aspects of our approach and present its applications for distinctiveness-guided shape retrieval, sampling, and view selection in 3D scenes.

中文翻译:

3D 形状上不同区域的无监督检测

本文提出了一种新的方法来学习和检测 3D 形状上的独特区域。与以前需要标记数据的工作不同,我们的方法是无监督的。我们对从 3D 形状采样的点集进行分析,然后为无监督的形状聚类任务制定和训练深度神经网络,以学习局部和全局特征,以区分相对于给定形状集的形状。为了驱动网络以无监督的方式学习,我们设计了一个基于聚类的非参数 softmax 分类器,该分类器具有形状的迭代重新聚类,以及用于提高特征嵌入质量和稳定学习过程的自适应对比损失。届时,我们鼓励网络学习输入形状上的点独特性。
更新日期:2020-06-01
down
wechat
bug