# Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians

arXiv: https://arxiv.org/abs/2303.08064 · HTML: https://mlsanity.com/paper/2303.08064/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 63 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Neural Control Variates](https://mlsanity.com/paper/2006.01524/) (2020)
- [Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets](https://mlsanity.com/paper/1412.7091/) (2014)
- [Path Guiding Using Spatio-Directional Mixture Models](https://mlsanity.com/paper/2111.13094/) (2021)
- [Online path sampling control with progressive spatio-temporal filtering](https://mlsanity.com/paper/2005.07547/) (2020)
- [Marginalizable Density Models](https://mlsanity.com/paper/2106.04741/) (2021)

## Built on by (most cited first, 6 of 6)

- [Vertex Features for Neural Global Illumination](https://mlsanity.com/paper/2508.07852/) (2025)
- [Neural Importance Sampling of Many Lights](https://mlsanity.com/paper/2505.11729/) (2025)
- [Neural Path Guiding with Distribution Factorization](https://mlsanity.com/paper/2506.00839/) (2025)
- [Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction](https://mlsanity.com/paper/2606.09794/) (2026)
- [RenderFormer++: Scalable and Physics-Informed Feed-Forward Neural Rendering](https://mlsanity.com/paper/2606.30380/) (2026)
- [Compact Neural Appearance Models for Efficient Gaussian Splatting](https://mlsanity.com/paper/2609.05255/) (2026)

## Abstract (arXiv)

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.