Spatiotemporal Variance-Guided Filtering:
Real-Time Reconstruction for Path-Traced Global Illumination

Christoph Schied, Anton Kaplanyan, Chris Wyman, Anjul Patney, Chakravarty R. Alla Chaitanya, John Burgess, Shiqiu Liu, Carsten Dachsbacher, Aaron Lefohn, Marco Salvi

Proceedings of High Performance Graphics 2017

Our filter takes (left) 1 sample per pixel path-traced input and (center) reconstructs a temporally stable 1920x1080 image in just 10ms. Compare to (right) a 2048 samples per pixel path-traced reference. Insets compare our input, our filtered results, and a reference on two regions, and show the impact filtered global illumination has over just direct illumination. Given the noisy input, notice the similarity to the reference for glossy reflections, global illumination, and direct soft shadows.


We introduce a reconstruction algorithm that generates a temporally stable sequence of images from one path-per-pixel global illumination. To handle such noisy input, we use temporal accumulation to increase the effective sample count and spatiotemporal luminance variance estimates to drive a hierarchical, image-space wavelet filter. This hierarchy allows us to distinguish between noise and detail at multiple scales using local luminance variance.
Physically based light transport is a long-standing goal for real-time computer graphics. While modern games use limited forms of ray tracing, physically based Monte Carlo global illumination does not meet their 30Hz minimal performance requirement. Looking ahead to fully dynamic real-time path tracing, we expect this to only be feasible using a small number of paths per pixel. As such, image reconstruction using low sample counts is key to bringing path tracing to real-time. When compared to prior interactive reconstruction filters, our work gives approximately 10x more temporally stable results, matches reference images 5-47% better (according to SSIM), and runs in just 10ms (+- 15%) on modern graphics hardware at 1920x1080 resolution.


Supplemental video