# Photon Field Networks for Dynamic Real-Time Volumetric Global Illumination

arXiv: https://arxiv.org/abs/2304.07338 · HTML: https://mlsanity.com/paper/2304.07338/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 67 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Light Field Neural Rendering](https://mlsanity.com/paper/2112.09687/) (2021)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Compressive Neural Representations of Volumetric Scalar Fields](https://mlsanity.com/paper/2104.04523/) (2021)
- [Fast Neural Representations for Direct Volume Rendering](https://mlsanity.com/paper/2112.01579/) (2021)
- [DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization](https://mlsanity.com/paper/2204.06504/) (2022)
- [Interactive Volume Visualization via Multi-Resolution Hash Encoding based Neural Representation](https://mlsanity.com/paper/2207.11620/) (2022)
- [Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution](https://mlsanity.com/paper/1906.06520/) (2019)
- [Learning Adaptive Sampling and Reconstruction for Volume Visualization](https://mlsanity.com/paper/2007.10093/) (2020)
- [Deep Volumetric Ambient Occlusion](https://mlsanity.com/paper/2008.08345/) (2020)
- [FoVolNet: Fast Volume Rendering using Foveated Deep Neural Networks](https://mlsanity.com/paper/2209.09965/) (2022)
- [Path Guiding Using Spatio-Directional Mixture Models](https://mlsanity.com/paper/2111.13094/) (2021)
- [A Stack-Free Traversal Algorithm for Left-Balanced k-d Trees](https://mlsanity.com/paper/2210.12859/) (2022)
- [Deep Photon Mapping](https://mlsanity.com/paper/2004.12069/) (2020)

## Built on by (most cited first, 2 of 2)

- [GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splatting](https://mlsanity.com/paper/2507.19718/) (2025)
- [DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Rendering](https://mlsanity.com/paper/2609.30658/) (2026)

## Abstract (arXiv)

Volume data is commonly found in many scientific disciplines, like medicine, physics, and biology. Experts rely on robust scientific visualization techniques to extract valuable insights from the data. Recent years have shown path tracing to be the preferred approach for volumetric rendering, given its high levels of realism. However, real-time volumetric path tracing often suffers from stochastic noise and long convergence times, limiting interactive exploration. In this paper, we present a novel method to enable real-time global illumination for volume data visualization. We develop Photon Field Networks -- a phase-function-aware, multi-light neural representation of indirect volumetric global illumination. The fields are trained on multi-phase photon caches that we compute a priori. Training can be done within seconds, after which the fields can be used in various rendering tasks. To showcase their potential, we develop a custom neural path tracer, with which our photon fields achieve interactive framerates even on large datasets. We conduct in-depth evaluations of the method's performance, including visual quality, stochastic noise, inference and rendering speeds, and accuracy regarding illumination and phase function awareness. Results are compared to ray marching, path tracing and photon mapping. Our findings show that Photon Field Networks can faithfully represent indirect global illumination across the phase spectrum while exhibiting less stochastic noise and rendering at a significantly faster rate than traditional methods.