BriefGPT.xyz
Feb, 2020
学习分组:一种针对未见类别的底部向上的三维零件发现框架
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
HTML
PDF
Tiange Luo, Kaichun Mo, Zhiao Huang, Jiarui Xu, Siyu Hu...
TL;DR
本研究提出一种基于学习的聚合聚类框架,在提取局部上下文以促进泛化到未知类别的情况下,学习部件的几何先验知识,并在不看到任何注释样本的情况下将其应用到未见过的类别中,实现了对大规模细粒度3D零件数据集PartNet的有效分割。
Abstract
We address the problem of discovering
3d parts
for objects in unseen categories. Being able to learn the
geometry prior
of parts and transfer this prior to unseen categories pose fundamental challenges on data-dr
→