NeuSample: Importance Sampling for Neural Materials
NeuSample: Importance Sampling for Neural Materials
复制标题
DOI：
10.1145/3588432.3591524
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Bing Xu;Liwen Wu;Miloš Hašan;Fujun Luan;Iliyan Georgiev;Zexiang Xu;R. Ramamoorthi
中科院分区：
文献类型：
--
作者：
Bing Xu;Liwen Wu;Miloš Hašan;Fujun Luan;Iliyan Georgiev;Zexiang Xu;R. Ramamoorthi
神经材料表示最近被提出来增强真实感渲染中使用的材料外观工具箱。这些模型是成功的任务范围从测量的BTF压缩，通过有效地渲染合成置换材料与闭塞，BSDF分层。然而，在大多数神经材料方法中，重要性采样一直是事后的想法，并且已经通过低效的余弦半球采样或将其与额外的简单分析叶混合来处理。在本文中，我们填补了这一空白，通过评估和比较各种pdf学习方法采样空间变化的神经材料，并提出这些方法的新变化。我们研究三种采样方法：分析叶混合，归一化流量，直方图预测。在每种类型中，我们都介绍了超越以前工作的改进，并在采样率，挂钟时间和最终视觉质量方面对这些方法进行了广泛的评估和比较。我们的标准化流和直方图混合版本性能良好，可用于实际渲染系统，可能有助于在生产中更广泛地采用神经材料模型。
Neural material representations have recently been proposed to augment the material appearance toolbox used in realistic rendering. These models are successful at tasks ranging from measured BTF compression, through efficient rendering of synthetic displaced materials with occlusions, to BSDF layering. However, importance sampling has been an after-thought in most neural material approaches, and has been handled by inefficient cosine-hemisphere sampling or mixing it with an additional simple analytic lobe. In this paper we fill that gap, by evaluating and comparing various pdf-learning approaches for sampling spatially varying neural materials, and proposing new variations of these approaches. We investigate three sampling approaches: analytic-lobe mixtures, normalizing flows, and histogram prediction. Within each type, we introduce improvements beyond previous work, and we extensively evaluate and compare these approaches in terms of sampling rate, wall-clock time, and final visual quality. Our versions of normalizing flows and histogram mixtures perform well and can be used in practical rendering systems, potentially facilitating the broader adoption of neural material models in production.