TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes
TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes
复制标题
DOI：
10.1109/cvpr.2019.00457
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Jingwei Huang;Haotian Zhang;L. Yi;T. Funkhouser;M. Nießner;L. Guibas
中科院分区：
文献类型：
--
作者：
Jingwei Huang;Haotian Zhang;L. Yi;T. Funkhouser;M. Nießner;L. Guibas
我们介绍了一种神经网络体系结构，该体系结构旨在从与3D表面网格(例如，颜色纹理贴图)相关联的高分辨率信号中提取特征。其关键思想是利用4-旋转对称(4-ROSY)场来定义曲面上的卷积区域。尽管4-ROSY场具有几个有利于曲面卷积的性质(低失真、奇点少、一致的参数化等)，但方向在任何采样点都是模糊的，最高可达4倍旋转。因此，我们引入了一种新的4-ROSE模糊度不变量卷积算子，并将其用于网络中从曲面测地线邻域上的高分辨率信号中提取特征。与缺乏方向概念的基于PointNet的方法等替代方法相比，这些邻域给出的连贯结构导致了明显更强的特征。作为一个示例应用，我们展示了我们的体系结构对于纹理3D网格的3D语义分割的好处。结果表明，在仅几何(6.4%)和RGB+几何(6.9-8.2%)的设置下，我们的方法在平均IOU的基础上都比所有现有的方法都有显著的优势。
We introduce, TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e.g., color texture maps). The key idea is to utilize a 4-rotational symmetric(4-RoSy) field to define a domain for convolution on a surface. Though 4-RoSy fields have several properties favor-able for convolution on surfaces (low distortion, few singularities, consistent parameterization, etc.), orientations are ambiguous up to 4-fold rotation at any sample point. So, we introduce a new convolutional operator invariant to the4-RoSy ambiguity and use it in a network to extract features from high-resolution signals on geodesic neighborhoods of a surface. In comparison to alternatives, such as PointNet-based methods which lack a notion of orientation, the coherent structure given by these neighborhoods results in significantly stronger features. As an example application, we demonstrate the benefits of our architecture for 3D semantic segmentation of textured 3D meshes. The results show that our method outperforms all existing methods on the basis of mean IoU by a significant margin in both geometry-only(6.4%) and RGB+Geometry (6.9-8.2%) settings.