Blockwise Multi-Order Feature Regression for Real-Time Path Tracing Reconstruction
2019, Koskela M., Immonen K., Mäkitalo M., Foi A., Viitanen T., Jääskeläinen P., Kultala H., and Takala J., In ACM Transactions on Graphics (TOG), Volume 38 Issue 5.
Abstract
Path tracing produces realistic results including global illumination using a unified simple rendering pipeline. Reducing the amount of noise to imperceptible levels without post-processing requires thousands of samples per pixel (spp), while currently it is only possible to render extremely noisy 1 spp frames in real time with desktop GPUs. However, post-processing can utilize feature buffers, which contain noise-free auxiliary data available in the rendering pipeline. Previously, regression-based noise filtering methods have only been used in offline rendering due to their high computational cost. In this paper we propose a novel regression-based reconstruction pipeline, called Blockwise Multi-Order Feature Regression (BMFR), tailored for pathtraced 1 spp inputs that runs in real time. The high speed is achieved with a fast implementation of augmented QR factorization and by using stochastic regularization to address rank-deficient feature data. The proposed algorithm is 1.8× faster than the previous state-of-the-art real-time path tracing reconstruction method while producing better quality frame sequences.
BibTeX
@article{koskela2019blockwise,
title={Blockwise Multi-Order Feature Regression for Real-Time Path Tracing Reconstruction},
author={Koskela, Matias and Immonen, Kalle and M\"{a}kitalo, Markku and Foi, Alessandro and Viitanen, Timo and J\"{a}\"{a}skel\"{a}inen, Pekka and Kultala, Heikki and Takala, Jarmo},
journal={ACM Transactions on Graphics (TOG)},
volume={38},
number={5},
month = jun,
year={2019},
doi={10.1145/3269978},
}
Video
YouTube causes a lot of artifacts and therefore we recommend downloading the original mp4 file.