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 2212.06344cs.CVcs.GR
收藏

DA Wand:使用神经网格参数化的失真感知选择

DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization

University of Chicago(芝加哥大学);Adobe Research(奥多比研究院)

Richard Liu, Noam Aigerman, Vladimir G. Kim, Rana Hanocka

摘要:

我们提出了一种神经技术学习选择一个局部的子区域周围的一个点,可用于网格参数化。我们框架的动机是由用于在表面上进行贴花,纹理或绘画的交互式工作流程驱动的。我们的主要思想是将分割概率作为经典参数化方法的权重,在神经网络框架内实现为一个新的可微参数化层。我们训练一个分割网络来选择3D区域,这些区域被参数化为2D并受到由此产生的失真的惩罚,从而产生失真感知的分割。训练后,用户可以使用我们的系统交互式地选择网格上的一个点,并获得一个大的,有意义的区域周围的选择,诱导低失真参数化。我们的代码和项目页面目前可用。

英文摘要:

We present a neural technique for learning to select a local sub-region around a point which can be used for mesh parameterization. The motivation for our framework is driven by interactive workflows used for decaling, texturing, or painting on surfaces. Our key idea is to incorporate segmentation probabilities as weights of a classical parameterization method, implemented as a novel differentiable parameterization layer within a neural network framework. We train a segmentation network to select 3D regions that are parameterized into 2D and penalized by the resulting distortion, giving rise to segmentations which are distortion-aware. Following training, a user can use our system to interactively select a point on the mesh and obtain a large, meaningful region around the selection which induces a low-distortion parameterization. Our code and project page are currently available.

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。

↑