DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization
DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization
复制标题
DOI：
10.1109/cvpr52729.2023.01606
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Richard Liu;Noam Aigerman;Vladimir G. Kim;Rana Hanocka
中科院分区：
文献类型：
--
作者：
Richard Liu;Noam Aigerman;Vladimir G. Kim;Rana Hanocka
我们提出了一种神经技术，用于学习选择一个点周围的局部子区域，该子区域可用于网格参数化。我们框架的动机是由用于表面贴花、纹理或绘画的交互式工作流程驱动的。我们的关键思想是将分割概率合并为经典参数化方法的权重，在神经网络框架内实现为新颖的可微分参数化层。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，并在选择周围获得一个大的、有意义的区域，从而产生低失真参数化。我们的代码11https://github.com/thirdle/DA-Wand 和项目22https://thirdle.github.io/DA-Wand/ 是公开的。
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 code11https://github.com/threedle/DA-Wand and project22https://threedle.github.io/DA-Wand/ are publicly available.