arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.03629cs.CVcs.GRcs.LG
收藏

VoronoiNet:具有局部支撑的一般函数逼近器

VoronoiNet: General Functional Approximators with Local Support

New York University(纽约大学);University of Victoria(维多利亚大学);Google Brain(谷歌大脑)

Francis Williams, Daniele Panozzo, Kwang Moo Yi, Andrea Tagliasacchi

摘要:

沃罗诺伊图是在各种图形应用中使用的高度紧凑的表示。在这项工作中,我们展示了如何通过一种新颖的深度架构将其可区分的版本嵌入到生成深度网络中。通过这样做,我们实现了一个高度紧凑的潜在嵌入,能够提供更详细的重建,无论是在2D和3D,为各种形状。在这份技术报告中,我们介绍了我们的表示,并提出了一组初步结果,将其与最近提出的隐式占用网络进行比较。

英文摘要:

Voronoi diagrams are highly compact representations that are used in various Graphics applications. In this work, we show how to embed a differentiable version of it -- via a novel deep architecture -- into a generative deep network. By doing so, we achieve a highly compact latent embedding that is able to provide much more detailed reconstructions, both in 2D and 3D, for various shapes. In this tech report, we introduce our representation and present a set of preliminary results comparing it with recently proposed implicit occupancy networks.

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。

↑