Machine Learning is the Solution Also for Foveated Path Tracing Reconstruction

Atro Lotvonen, Matias Koskela, Pekka Jääskeläinen

2020

Abstract

Real-time photorealistic rendering requires a lot of computational power. Foveated rendering reduces the work by focusing the effort to where the user is looking, but the very sparse sampling in the periphery requires fast reconstruction algorithms with good quality. The problem is even more complicated in the field of foveated path tracing where the sparse samples are also noisy. In this position paper we argue that machine learning and data-driven methods play an important role in the future of real-time foveated rendering. In order to show initial proofs to support this opinion, we propose a preliminary machine learning based method which is able to improve the reconstruction quality of foveated path traced image by using spatio-temporal input data. Moreover, the method is able to run in the same reduced foveated resolution as the path tracing setup. The reconstruction using the preliminary network is about 2.9ms per 658×960 frame on a GeForce RTX 2080 Ti GPU.

Paper Citation

in Harvard Style

Lotvonen A., Koskela M. and Jääskeläinen P. (2020). Machine Learning is the Solution Also for Foveated Path Tracing Reconstruction. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP; ISBN 978-989-758-402-2, SciTePress, pages 361-367. DOI: 10.5220/0009156303610367

in Bibtex Style

@conference{grapp20,
author={Atro Lotvonen and Matias Koskela and Pekka Jääskeläinen},
title={Machine Learning is the Solution Also for Foveated Path Tracing Reconstruction},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP},
year={2020},
pages={361-367},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009156303610367},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP
TI - Machine Learning is the Solution Also for Foveated Path Tracing Reconstruction
SN - 978-989-758-402-2
AU - Lotvonen A.
AU - Koskela M.
AU - Jääskeläinen P.
PY - 2020
SP - 361
EP - 367
DO - 10.5220/0009156303610367
PB - SciTePress