Learning Shape Abstractions by Assembling Volumetric Primitives

被引：234

作者：

Tulsiani, Shubham ^{[1
]}

Su, Hao ^{[2
]}

Guibas, Leonidas J. ^{[2
]}

Efros, Alexei A. ^{[1
]}

Malik, Jitendra ^{[1
]}

机构：

[1] Univ Calif Berkeley, Berkeley, CA 94720 USA

[2] Stanford Univ, Stanford, CA 94305 USA

来源：

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/CVPR.2017.160

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives. In addition to generating simple and geometrically interpretable explanations of 3D objects, our framework also allows us to automatically discover and exploit consistent structure in the data. We demonstrate that using our method allows predicting shape representations which can be leveraged for obtaining a consistent parsing across the instances of a shape collection and constructing an interpretable shape similarity measure. We also examine applications for image-based prediction as well as shape manipulation.

引用

页码：1466 / 1474

页数：9