arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.13168cs.GRcs.CVcs.LG
收藏

SPAGHETTI:通过部件感知生成编辑隐式数据库

SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation

Tel Aviv University(特拉维夫大学);NVIDIA(英伟达);ETH Zurich(苏黎世联邦理工学院)

Amir Hertz, Or Perel, Raja Giryes, Olga Sorkine-Hornung, Daniel Cohen-Or

摘要:

神经隐场作为一种有吸引力的表示方法正在迅速出现,用于基于学习的技术。然而,采用它们进行3D形状建模和编辑是具有挑战性的。本文介绍了一种通过$\mathbf{P}$和$\mathbf{A}$软件$\mathbf{S}$ $\mathbf{T}$(简称SPAGHETTI)来编辑$\mathbf{T}$的方法。我们的体系结构允许隐式形状的操纵,通过变换,插值和组合形状段在一起,而不需要明确的部分监督。SPAGHETTI将形状部分表示分解为外部和内部几何信息。这一特性使得生成框架具有部分级控制。SPAGHETTI的建模功能使用交互式图形界面进行演示,用户可以直接编辑神经隐式形状。

英文摘要:

Neural implicit fields are quickly emerging as an attractive representation for learning based techniques. However, adopting them for 3D shape modeling and editing is challenging. We introduce a method for $\mathbf{E}$diting $\mathbf{I}$mplicit $\mathbf{S}$hapes $\mathbf{T}$hrough $\mathbf{P}$art $\mathbf{A}$ware $\mathbf{G}$enera$\mathbf{T}$ion, permuted in short as SPAGHETTI. Our architecture allows for manipulation of implicit shapes by means of transforming, interpolating and combining shape segments together, without requiring explicit part supervision. SPAGHETTI disentangles shape part representation into extrinsic and intrinsic geometric information. This characteristic enables a generative framework with part-level control. The modeling capabilities of SPAGHETTI are demonstrated using an interactive graphical interface, where users can directly edit neural implicit shapes.

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。

↑