GraphDeco

Neural Precomputed Radiance Transfer
Presentation | Team members | Collaborations | Publications | Job offers | Contact

 

Neural Precomputed Radiance Transfer

Computer Graphics Forum (Proceedings of the Eurographics conference), Volume 41, Number 2 - April 2022
Download the publication : nprt.pdf [51.4Mo]  
Recent advances in neural rendering indicate immense promise for architectures that learn light transport, allowing efficient rendering of global illumination effects once such methods are trained. The training phase of these methods can be seen as a form of pre-computation, which has a long standing history in Computer Graphics. In particular, Pre-computed Radiance Transfer (PRT) achieves real-time rendering by freezing some variables of the scene (geometry, materials) and encoding the distribution of others, allowing interactive rendering at runtime. We adopt the same configuration as PRT – global illumination of static scenes under dynamic environment lighting – and investigate different neural network architectures, inspired by the design principles and theoretical analysis of PRT. We introduce four different architectures, and show that those based on knowledge of light transport models and PRT-inspired principles improve the quality of global illumination predictions at equal training time and network size, without the need for high-end ray-tracing hardware.

Images and movies

 

See also

More information

Project page here includes supplemental material and datasets and link to the code

Acknowledgements and Funding

This research was funded by the ERC Advanced grant FUNGRAPH No 788065 (http://fungraph.inria.fr). The authors are grateful to the OPAL infrastructure from Université Côte d’Azur for providing resources and support. The authors would also like to thank Adobe for their generous donations, and acknowledge Fabrice Rousselle for helping with the comparison to NRC by running the code on our scenes. Finally, the authors thank the anonymous reviewers for their valuable feedback.

BibTex references

@Article{RBRD22,
  author       = "Rainer, Gilles and Bousseau, Adrien and Ritschel, Tobias and Drettakis, George",
  title        = "Neural Precomputed Radiance Transfer",
  journal      = "Computer Graphics Forum (Proceedings of the Eurographics conference)",
  number       = "2",
  volume       = "41",
  month        = "April",
  year         = "2022",
  url          = "http://www-sop.inria.fr/reves/Basilic/2022/RBRD22"
}

Other publications in the database

» Adrien Bousseau
» Tobias Ritschel
» George Drettakis