In this article, we introduce a compact representation for measured BRDFs by leveraging Neural Processes (NPs). Unlike prior methods that express those BRDFs as discrete high-dimensional matrices or tensors, our technique considers measured BRDFs as continuous functions and works in corresponding function spaces . Specifically, provided the evaluations of a set of BRDFs, such as ones in MERL and EPFL datasets, our method learns a low-dimensional latent space as well as a few neural networks to encode and decode these measured BRDFs or new BRDFs into and from this space in a non-linear fashion. Leveraging this latent space and the flexibility offered by the NPs formulation, our encoded BRDFs are highly compact and offer a level of accuracy better than prior methods. We demonstrate the practical usefulness of our approach via two important applications, BRDF compression and editing. Additionally, we design two alternative post-trained decoders to, respectively, achieve better compression ratio for individual BRDFs and enable importance sampling of BRDFs.

中文翻译：

---

使用神经过程的测量 BRDF 的紧凑表示

在本文中，我们通过利用神经过程 (NP) 介绍了测量 BRDF 的紧凑表示。与将这些 BRDF 表示为离散的高维矩阵或张量的先前方法不同，我们的技术将测量的 BRDF 视为连续函数并在相应的工作功能空间. 具体来说，提供一组 BRDF 的评估，例如 MERL 和 EPFL 数据集中的那些，我们的方法学习一个低维潜在空间以及一些神经网络来编码和解码这些测量的 BRDF 或新的 BRDF非线性空间。利用这种潜在空间和 NPs 公式提供的灵活性，我们编码的 BRDF 非常紧凑，并且提供了比以前的方法更好的精度水平。我们通过两个重要的应用程序（BRDF 压缩和编辑）展示了我们的方法的实际用途。此外，我们设计了两个替代的后训练解码器，分别为单个 BRDF 实现更好的压缩比，并实现 BRDF 的重要性采样。