计算机科学
人工智能
利用
卷积神经网络
对象(语法)
模式识别(心理学)
机器学习
数据挖掘
计算机安全
作者
Charles R. Qi,Hao Su,Matthias NieBner,Angela Dai,Mengyuan Yan,Leonidas J. Guibas
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2016-06-01
卷期号:: 5648-5656
被引量:1756
标识
DOI:10.1109/cvpr.2016.609
摘要
3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-theart methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view representations. Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations. In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches. To this end, we introduce two distinct network architectures of volumetric CNNs. In addition, we examine multi-view CNNs, where we introduce multiresolution filtering in 3D. Overall, we are able to outperform current state-of-the-art methods for both volumetric CNNs and multi-view CNNs. We provide extensive experiments designed to evaluate underlying design choices, thus providing a better understanding of the space of methods available for object classification on 3D data.
科研通智能强力驱动
Strongly Powered by AbleSci AI