arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1604.03265cs.CVcs.AI
收藏

用于3D数据对象分类的体积和多视图CNN

Volumetric and Multi-View CNNs for Object Classification on 3D Data

Stanford University(斯坦福大学)

Charles R. Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, Leonidas J. Guibas

摘要:

3D形状模型变得越来越广泛,并且更容易捕获,使得可用的3D信息对于对象分类的进展至关重要。目前最先进的方法依赖于CNN来解决这个问题。最近,我们看到两种类型的CNN正在开发:基于体积表示的CNN与基于多视图表示的CNN。这两种类型CNN的经验结果显示出很大的差距,表明现有的体积CNN架构和方法无法充分利用3D表示的能力。在本文中,我们的目标是根据对现有方法的广泛分析来改进体积CNN和多视图CNN。为此,我们介绍了两种不同的体积CNN网络架构。此外,我们还研究了多视图CNN,其中我们在3D中引入了多分辨率滤波。总的来说,我们能够在体积CNN和多视图CNN方面胜过当前最先进的方法。我们提供了广泛的实验,旨在评估潜在的设计选择,从而提供了一个更好的理解空间的方法可用于对象分类的3D数据。

英文摘要:

3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-the-art 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 multi-resolution 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑