arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.10705cs.CV
收藏

基于一般覆盖的曲面网络

Surface Networks via General Covers

Weizmann Institute of Science(魏茨曼科学研究所)

Niv Haim, Nimrod Segol, Heli Ben-Hamu, Haggai Maron, Yaron Lipman

摘要:

开发几何数据的深度学习技术是一个活跃且富有成果的研究领域。本文通过开发一种新的表面到图像表示来解决球形表面学习的问题。使用这种表示,我们能够快速地使成功的CNN模型适应表面设置。表面图像表示基于从图像域到表面的覆盖映射。也就是说,贴图会多次环绕曲面,以确保曲面的每个部分都能在图像中得到很好的表示。与以前的表面到图像表示不同,我们在单个图像中提供了所有表面部分的低失真覆盖。具体来说,对于学习球形信号的用例,我们的表示为深度学习中使用的几种流行的球形参数化提供了一种低失真的替代方案。我们已经使用表面到图像表示将标准CNN架构应用于3D模型以及球形信号。我们表明,我们的方法实现了最先进的形状检索,形状分类和语义形状分割的任务或可比的结果。

英文摘要:

Developing deep learning techniques for geometric data is an active and fruitful research area. This paper tackles the problem of sphere-type surface learning by developing a novel surface-to-image representation. Using this representation we are able to quickly adapt successful CNN models to the surface setting. The surface-image representation is based on a covering map from the image domain to the surface. Namely, the map wraps around the surface several times, making sure that every part of the surface is well represented in the image. Differently from previous surface-to-image representations, we provide a low distortion coverage of all surface parts in a single image. Specifically, for the use case of learning spherical signals, our representation provides a low distortion alternative to several popular spherical parameterizations used in deep learning. We have used the surface-to-image representation to apply standard CNN architectures to 3D models as well as spherical signals. We show that our method achieves state of the art or comparable results on the tasks of shape retrieval, shape classification and semantic shape segmentation.

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。

↑