RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing

Abstract summary

This rendering framework learns where to spend path-tracing samples and how to reconstruct a clean image from them. Reinforcement learning trains the sampling policy, while a learned latent representation retains individual sample information for a neural denoiser. Joint training replaces hand-designed temporal and spatial aggregation rules and improves the trade-off between rendering time and visual quality.

Abstract on arXiv

DOI arXiv PDF Paper

Cite this work

@misc{rlbasedstatefulneuraladaptivesamplinganddenoisingforrealtimepathtracing,
  title = {RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing},
  author = {Antoine Scardigli and Lukas Cavigelli and Lorenz K. Müller},
  year = {2023},
  note = {NeurIPS},
  url = {https://doi.org/10.52202/075280-2898}
}

Download