Real-time neural radiance caching for path tracing
Real-time neural radiance caching for path tracing
复制标题
DOI：
10.1145/3476576.3476579
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
T. Müller;Fabrice Rousselle;J. Nov'ak;A. Keller
中科院分区：
文献类型：
--
作者：
T. Müller;Fabrice Rousselle;J. Nov'ak;A. Keller
我们提出了一种实时神经辐射缓存方法的路径跟踪全局照明。我们的系统旨在处理完全动态的场景，并且不对照明，几何形状和材料做任何假设。数据驱动的性质，我们的方法回避了许多困难的缓存算法，如定位，插值和更新缓存点。由于预训练神经网络来处理新的动态场景是一个艰巨的泛化挑战，因此我们取消了预训练，而是通过自适应实现泛化，即我们选择在渲染时训练辐射缓存。我们采用自我训练来提供低噪声训练目标，并通过迭代少量反弹训练更新来模拟无限反弹传输。更新和缓存查询会产生轻微的开销-全高清分辨率下约2.6ms-这要归功于充分利用现代硬件的神经网络的流实现。我们证明了显着的噪声降低的成本，很少引起的偏见，并报告国家的最先进的，实时性能的一些具有挑战性的情况。
We present a real-time neural radiance caching method for path-traced global illumination. Our system is designed to handle fully dynamic scenes, and makes no assumptions about the lighting, geometry, and materials. The data-driven nature of our approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation, i.e. we opt for training the radiance cache while rendering. We employ self-training to provide low-noise training targets and simulate infinite-bounce transport by merely iterating few-bounce training updates. The updates and cache queries incur a mild overhead---about 2.6ms on full HD resolution---thanks to a streaming implementation of the neural network that fully exploits modern hardware. We demonstrate significant noise reduction at the cost of little induced bias, and report state-of-the-art, real-time performance on a number of challenging scenarios.