A Shape‐Aware Model for Discrete Texture Synthesis
A Shape‐Aware Model for Discrete Texture Synthesis
复制标题
DOI：
10.1111/cgf.12152
复制
发表时间：
2013-06
影响因子：
2.5
通讯作者：
Pierre-Edouard Landes;B. Galerne;Thomas Hurtut
中科院分区：
文献类型：
--
作者：
Pierre-Edouard Landes;B. Galerne;Thomas Hurtut
我们提出了一种新颖的形状感知方法，用于合成由不同矢量图形对象的集合组成的 2D 和 3D 离散元素纹理。扩展了经过长期验证的点过程框架，我们提出了一种形状过程，一种基于空间测量的新颖随机模型，充分考虑了元素的几何形状。我们通过示例证明我们的方法非常适合离散纹理合成。我们的模型可以通过蒙特卡罗采样实现稳健的统计参数估计和可靠的输出生成。我们的大量实验表明，与当前最先进的技术相反，我们的算法设法捕获各向异性元素分布并系统地防止物体之间发生不良碰撞。
We present a novel shape‐aware method for synthesizing 2D and 3D discrete element textures consisting of collections of distinct vector graphics objects. Extending the long‐proven point process framework, we propose a shape process, a novel stochastic model based on spatial measurements that fully take into account the geometry of the elements. We demonstrate that our approach is well‐suited for discrete texture synthesis by example. Our model enables for both robust statistical parameter estimation and reliable output generation by Monte Carlo sampling. Our numerous experiments show that contrary to current state‐of‐the‐art techniques, our algorithm manages to capture anisotropic element distributions and systematically prevents undesirable collisions between objects.