# Active Exploration for Neural Global Illumination of Variable Scenes

arXiv: https://arxiv.org/abs/2203.08272 · HTML: https://mlsanity.com/paper/2203.08272/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 66 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020)
- [Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning](https://mlsanity.com/paper/1902.03932/) (2019)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Stochastic Optimization with Importance Sampling](https://mlsanity.com/paper/1401.2753/) (2014)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Generative Adversarial Active Learning](https://mlsanity.com/paper/1702.07956/) (2017)
- [Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks](https://mlsanity.com/paper/1809.00886/) (2018)
- [Deep Shading: Convolutional Neural Networks for Screen-Space Shading](https://mlsanity.com/paper/1603.06078/) (2016)
- [Neural Radiosity](https://mlsanity.com/paper/2105.12319/) (2021)
- [X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation](https://mlsanity.com/paper/2010.00450/) (2020)
- [Safe Adaptive Importance Sampling](https://mlsanity.com/paper/1711.02637/) (2017)
- [Online Learning to Sample](https://mlsanity.com/paper/1506.09016/) (2015)
- [Learning to Importance Sample in Primary Sample Space](https://mlsanity.com/paper/1808.07840/) (2018)

## Built on by (most cited first, 11 of 11)

- [Pointersect: Neural Rendering with Cloud-Ray Intersection](https://mlsanity.com/paper/2304.12390/) (2023)
- [N-Dimensional Gaussians for Fitting of High Dimensional Functions](https://mlsanity.com/paper/2405.20067/) (2024)
- [Learning to Learn and Sample BRDFs](https://mlsanity.com/paper/2210.03510/) (2022)
- [Neural Free-Viewpoint Relighting for Glossy Indirect Illumination](https://mlsanity.com/paper/2307.06335/) (2023)
- [Generative AI in Agriculture: Creating Image Datasets Using DALL.E's Advanced Large Language Model Capabilities](https://mlsanity.com/paper/2307.08789/) (2023)
- [Vertex Features for Neural Global Illumination](https://mlsanity.com/paper/2508.07852/) (2025)
- [A Generalizable Light Transport 3D Embedding for Global Illumination](https://mlsanity.com/paper/2510.18189/) (2025)
- [Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials](https://mlsanity.com/paper/2509.07522/) (2025)
- [Melon Fruit Detection and Quality Assessment Using Generative AI-Based Image Data Augmentation](https://mlsanity.com/paper/2407.10413/) (2024)
- [OctaOctree Neural Radiosity for Real-time Glossy Material Rendering](https://mlsanity.com/paper/2606.08469/) (2026)
- [RenderFormer++: Scalable and Physics-Informed Feed-Forward Neural Rendering](https://mlsanity.com/paper/2606.30380/) (2026)

## Abstract (arXiv)

Neural rendering algorithms introduce a fundamentally new approach for photorealistic rendering, typically by learning a neural representation of illumination on large numbers of ground truth images. When training for a given variable scene, i.e., changing objects, materials, lights and viewpoint, the space D of possible training data instances quickly becomes unmanageable as the dimensions of variable parameters increase. We introduce a novel Active Exploration method using Markov Chain Monte Carlo, which explores D, generating samples (i.e., ground truth renderings) that best help training and interleaves training and on-the-fly sample data generation. We introduce a self-tuning sample reuse strategy to minimize the expensive step of rendering training samples. We apply our approach on a neural generator that learns to render novel scene instances given an explicit parameterization of the scene configuration. Our results show that Active Exploration trains our network much more efficiently than uniformly sampling, and together with our resolution enhancement approach, achieves better quality than uniform sampling at convergence. Our method allows interactive rendering of hard light transport paths (e.g., complex caustics) -- that require very high samples counts to be captured -- and provides dynamic scene navigation and manipulation, after training for 5-18 hours depending on required quality and variations.