Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians

• Published in: ACM transactions on graphics 2024-06, Vol.43 (3), p.1-18, Article 26
• Main Authors: Huang, Jiawei, Iizuka, Akito, Tanaka, Hajime, Komura, Taku, Kitamura, Yoshifumi
• Format: Article
• Language: English
• Subjects: Computing methodologies; Mathematics of computing; Probabilistic algorithms; Ray tracing; Reinforcement learning; Rendering
• ISSN: 0730-0301; 1557-7368
• DOI: 10.1145/3649310

Importance sampling techniques significantly reduce variance in physically based rendering. In this article, we propose a novel online framework to learn the spatial-varying distribution of the full product of the rendering equation, with a single small neural network using stochastic ray samples. The learned distributions can be used to efficiently sample the full product of incident light. To accomplish this, we introduce a novel closed-form density model, called the Normalized Anisotropic Spherical Gaussian mixture, that can model a complex light field with a small number of parameters and that can be directly sampled. Our framework progressively renders and learns the distribution, without requiring any warm-up phases. With the compact and expressive representation of our density model, our framework can be implemented entirely on the GPU, allowing it to produce high-quality images with limited computational resources. The results show that our framework outperforms existing neural path guiding approaches and achieves comparable or even better performance than state-of-the-art online statistical path guiding techniques.