Rendering Neural Materials on Curved Surfaces
Rendering Neural Materials on Curved Surfaces
复制标题
DOI：
10.1145/3528233.3530721
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Alexandr Kuznetsov;Xuezheng Wang;Krishna Mullia;Fujun Luan;Zexiang Xu;Miloš Hašan;R. Ramamoorthi
中科院分区：
文献类型：
--
作者：
Alexandr Kuznetsov;Xuezheng Wang;Krishna Mullia;Fujun Luan;Zexiang Xu;Miloš Hašan;R. Ramamoorthi
神经材质反射率表示解决了带有参数纹理的传统分析 BRDF 的一些局限性；理论上它们可以表示任何材料数据，无论是具有位移、阴影和相互反射的复杂合成微观几何形状，还是真实测量的反射率。然而，它们仍然在无限平面上近似材质，这使得它们无法正确处理接近放牧方向的轮廓和视差效果。本文的目标是设计一种能够正确处理此类轮廓效果的神经材料表示。我们扩展神经网络查询以将表面曲率信息作为输入，而查询输出则扩展为除了反射率之外还返回透明度值。我们在包含跨越各种表面曲率的查询的合成数据上训练新的神经表示。我们展示了准确表示复杂轮廓行为的能力，这在传统上需要更昂贵且不太灵活的技术，例如动态几何位移或光线行进。
Neural material reflectance representations address some limitations of traditional analytic BRDFs with parameter textures; they can theoretically represent any material data, whether a complex synthetic microgeometry with displacements, shadows and inter-reflections, or real measured reflectance. However, they still approximate the material on an infinite plane, which prevents them from correctly handling silhouette and parallax effects for viewing directions close to grazing. The goal of this paper is to design a neural material representation capable of correctly handling such silhouette effects. We extend the neural network query to take surface curvature information as input, while the query output is extended to return a transparency value in addition to reflectance. We train the new neural representation on synthetic data that contains queries spanning a variety of surface curvatures. We show an ability to accurately represent complex silhouette behavior that would traditionally require more expensive and less flexible techniques, such as on-the-fly geometry displacement or ray marching.