Stochastic Pairwise MIS for Unbiased Large-Kernel Reuse in Real-Time
Loading...
Date
2026
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Spatiotemporal resampling methods such as ReSTIR decrease noise in Monte Carlo rendering of dynamic content by reusing paths across frames and pixels. Standard ReSTIR reuses spatially from a small number of randomly selected neighbors. This reuse suffers when few neighbors contain contributing samples, reducing quality toward that of the underlying path sampler. This commonly occurs during camera or object motion, as regions not present in prior frames are revealed. Increasing the number of spatial neighbors helps but also increases cost. We propose a novel spatial neighbor selection technique, stochastic pairwise MIS, which enables unbiased reuse from many neighbors in real time and focuses reuse on pixels with contributing samples. This provides a significant increase in image quality overall, especially in regions with poor input samples.
Description
@article{10.1111:cgf.70391,
journal = {Computer Graphics Forum},
title = {{Stochastic Pairwise MIS for Unbiased Large-Kernel Reuse in Real-Time}},
author = {Hedstrom, Trevor and Kettunen, Markus and Lin, Daqi and Wyman, Chris and Li, Tzu-Mao},
year = {2026},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70391}
}