Bidirectional reflectance distribution functions (BRDFs) are pervasively used in computer graphics to produce realistic physically-based appearance. In recent years, several works explored using neural networks to represent BRDFs, taking advantage of neural networks' high compression rate and their ability to fit highly complex functions. However, once represented, the BRDFs will be fixed and therefore lack flexibility to take part in follow-up operations. In this paper, we present a form of "Neural BRDF algebra", and focus on both representation and operations of BRDFs at the same time. We propose a representation neural network to compress BRDFs into latent vectors, which is able to represent BRDFs accurately. We further propose several operations that can be applied solely in the latent space, such as layering and interpolation. Spatial variation is straightforward to achieve by using textures of latent vectors. Furthermore, our representation can be efficiently evaluated and sampled, providing a competitive solution to more expensive Monte Carlo layering approaches.
翻译:计算机图形中广泛使用双向反射分布功能(BRDFs),以产生现实的物理外观。近年来,利用神经网络探索了若干工程,利用神经网络代表BRDFs,利用神经网络的高压缩率及其适应高度复杂功能的能力。然而,一旦被代表,BRDFs将固定下来,因此缺乏参与后续行动的灵活性。在本文中,我们展示了一种“Neural BRDF代代数”的形式,同时侧重于BRDFs的代表和运行。我们提议了一个代表神经网络,将BRDFs压缩成潜在矢量,从而能够准确地代表BRDFs。我们进一步提议了一些仅可在潜在空间应用的操作,如层层层和内层。通过使用潜在矢量的纹理可以直接实现空间变异。此外,我们的代表性可以高效地评估和抽样,为更昂贵的蒙特卡洛层方法提供一个竞争性解决方案。