BriefGPT.xyz
Mar, 2021
学习三维物体的细粒度分割,无需部件标签
Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
HTML
PDF
Xiaogang Wang, Xun Sun, Xinyu Cao, Kai Xu, Bin Zhou
TL;DR
本文介绍了一种以深度聚类为基础的三维形状部分分割方法, 通过学习来自具有细颗粒度分割但没有零件标签的形状数据集的部分先验, 它通过最小化新型低秩损失来实现部分分割并表现出优秀的性能。
Abstract
Learning-based
3d shape segmentation
is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags. This assumption, however, is impractical for learning
→