Paper ID: 2303.08064

Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians

Jiawei Huang, Akito Iizuka, Hajime Tanaka, Taku Komura, Yoshifumi Kitamura

The variance reduction speed of physically-based rendering is heavily affected by the adopted importance sampling technique. In this paper we propose a novel online framework to learn the spatial-varying density model with a single small neural network using stochastic ray samples. To achieve this task, we propose a novel closed-form density model called the normalized anisotropic spherical gaussian mixture, that can express complex irradiance fields with a small number of parameters. Our framework learns the distribution in a progressive manner and does not need any warm-up phases. Due to the compact and expressive representation of our density model, our framework can be implemented entirely on the GPU, allowing it produce high quality images with limited computational resources.

Submitted: Mar 11, 2023