论文标题
神经卷积表面
Neural Convolutional Surfaces
论文作者
论文摘要
这项工作涉及形状的表示，该形状将细小的，局部和可能重复的几何形状从全球，粗糙的结构中解脱出来。实现此类分离会带来两个不相关的优势：i）代表给定几何形状所需的参数数量的显着压缩； ii）能够操纵全球几何形状或本地细节而不会损害对方的能力。我们方法的核心是一种新型的管道和神经结构，该管道被优化为代表一个特定地图集，代表一个3D表面。我们的管道和体系结构的设计是，以完全无监督的方式通过优化来实现全球几何形状的分离。我们表明，这种方法比艺术的状态达到了更好的神经形状压缩，并且能够操纵和转移形状细节。项目页面http://geometry.cs.ucl.ac.uk/projects/2022/cnnmaps/。
This work is concerned with a representation of shapes that disentangles fine, local and possibly repeating geometry, from global, coarse structures. Achieving such disentanglement leads to two unrelated advantages: i) a significant compression in the number of parameters required to represent a given geometry; ii) the ability to manipulate either global geometry, or local details, without harming the other. At the core of our approach lies a novel pipeline and neural architecture, which are optimized to represent one specific atlas, representing one 3D surface. Our pipeline and architecture are designed so that disentanglement of global geometry from local details is accomplished through optimization, in a completely unsupervised manner. We show that this approach achieves better neural shape compression than the state of the art, as well as enabling manipulation and transfer of shape details. Project page at http://geometry.cs.ucl.ac.uk/projects/2022/cnnmaps/ .
