Learning generative models for rendering specular microgeometry
Learning generative models for rendering specular microgeometry
复制标题
DOI：
10.1145/3355089.3356525
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Alexandr Kuznetsov;Miloš Hašan;Zexiang Xu;Ling-Qi Yan;B. Walter;N. Kalantari;Steve Marschner;R. Ramamoorthi
中科院分区：
文献类型：
--
作者：
Alexandr Kuznetsov;Miloš Hašan;Zexiang Xu;Ling-Qi Yan;B. Walter;N. Kalantari;Steve Marschner;R. Ramamoorthi
绘制镜面材质外观是计算机图形学的核心问题。虽然光滑的分析材料模型被广泛使用，但真实的镜面高光的高频结构需要考虑离散的有限微观几何形状。我们提出了一个新的方向：通过训练生成对抗网络（GAN），从合成或测量的示例中学习高频方向模式，而不是对表面微观结构进行显式建模和模拟（这在以前的工作中进行了探索）。将GAN合成应用于空间变化的BRDF的一个关键挑战是评估单个位置和方向的反射率，而无需评估整个半球。我们解决这个问题，使用一种新的方法，发电机网络的部分评估。我们还能够使用条件GAN方法控制大规模空间纹理。我们的方法的好处包括能够合成空间大的结果，而无需重复，支持从测量数据中学习，以及独立于数据集合成或测量的复杂性的评估性能。
Rendering specular material appearance is a core problem of computer graphics. While smooth analytical material models are widely used, the high-frequency structure of real specular highlights requires considering discrete, finite microgeometry. Instead of explicit modeling and simulation of the surface microstructure (which was explored in previous work), we propose a novel direction: learning the high-frequency directional patterns from synthetic or measured examples, by training a generative adversarial network (GAN). A key challenge in applying GAN synthesis to spatially varying BRDFs is evaluating the reflectance for a single location and direction without the cost of evaluating the whole hemisphere. We resolve this using a novel method for partial evaluation of the generator network. We are also able to control large-scale spatial texture using a conditional GAN approach. The benefits of our approach include the ability to synthesize spatially large results without repetition, support for learning from measured data, and evaluation performance independent of the complexity of the dataset synthesis or measurement.