arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.05418cs.LGcs.GRstat.ML
收藏

深度散射:用辐射预测神经网络绘制大气云

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks

Disney Research(迪士尼研究院);ETH Zürich(苏黎世联邦理工学院)

Simon Kallweit, Thomas Müller, Brian McWilliams, Markus Gross, Jan Novák

摘要:

我们提出了一种技术,有效地合成图像的大气云使用的Monte Carlo积分和神经网络相结合。复杂的Lorenz-Mie散射和形成云的气溶胶的高散射度使得云的渲染-例如,内部物体的特征性镀银和“白度”-对于仅基于蒙特卡罗积分或扩散理论的方法具有挑战性。我们处理问题的方式不同。在渲染过程中,我们没有模拟所有的光传输,而是从数十个云样本中预先学习辐射通量的空间和方向分布。为了渲染一个新的场景,我们采样云的可见点,并为每个点提取云的几何形状相对于阴影位置和光源的分层3D描述符。该描述符被输入到深度神经网络,该深度神经网络预测每个着色配置的辐射函数。我们的关键观察结果是,逐步将分层描述符输入到网络中,可以提高网络的学习速度,并在使用较少系数的情况下实现高精度预测。我们还采用了剩余连接的块设计,以进一步提高性能。我们的方法的GPU实现合成的云的图像,几乎无法区分的参考解决方案在几秒钟内交互。因此,我们的方法代表了云设计等应用程序的可行解决方案,并且由于其时间稳定性,也适用于高质量的动画内容制作。

英文摘要:

We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds---e.g. the characteristic silverlining and the "whiteness" of the inner body---challenging for methods based solely on Monte Carlo integration or diffusion theory. We approach the problem differently. Instead of simulating all light transport during rendering, we pre-learn the spatial and directional distribution of radiant flux from tens of cloud exemplars. To render a new scene, we sample visible points of the cloud and, for each, extract a hierarchical 3D descriptor of the cloud geometry with respect to the shading location and the light source. The descriptor is input to a deep neural network that predicts the radiance function for each shading configuration. We make the key observation that progressively feeding the hierarchical descriptor into the network enhances the network's ability to learn faster and predict with high accuracy while using few coefficients. We also employ a block design with residual connections to further improve performance. A GPU implementation of our method synthesizes images of clouds that are nearly indistinguishable from the reference solution within seconds interactively. Our method thus represents a viable solution for applications such as cloud design and, thanks to its temporal stability, also for high-quality production of animated content.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑