Bathroom
The Bathroom is a typical interior scene with a mix of textured glossy and diffuse materials that is easy to render for a unidirectional path tracer due to large light sources: the windows are modeled as diffuse area emitters. The bump-mapped surfaces are a challenge for local-frame-based guiding methods, such as the GMMs by Vorba et al. [2014] and are handled more gracefully by world-frame-based techniques such as PPG [Müller et al. 2017] and our NPG. In this scene, radiance-based guiding performs worse than unidirectional path tracing due to a rough dielectric glass panel directly in front of the light sources. Product-based techniques, like our NPG-Product, are able to take such BSDF properties into account and are able to significantly improve upon the performance of unidirectional path tracing at equal sample counts. Primary-sample-space path-sampling techniques offer little to no benefit over unidirectional path tracing with our NPS slightly outperforming PSSPS [Guo et al. 2018] with an equal number of samples.
Use mouse wheel to zoom in/out, click and drag to pan. Press keys [1], [2], ... to switch between individual images. Press [?] to see more keybindings.
Charts
Lower values are better (for SSIM, we plot 1-SSIM).
MAPE
SMAPE
L1
MRSE
L2
1-SSIM
Metrics
Metric | Path Tracing | PPG | GMM | PSSPS | NPS KL | NPG-Radiance KL | NPG-Product KL scalar | NPG-Product KL | NPG-Product χ² |
---|---|---|---|---|---|---|---|---|---|
Mega Samples | 236 | 236 | 236 | 236 | 236 | 236 | 236 | 236 | 236 |
Render Time | 88s | 2.3m | 10m | 89s | 3.5m | 9.3m | 11m | 12m | 15m |
MAPE | 0.147 | 0.189 | 0.272 | 0.143 | 0.146 | 0.178 | 0.0714 | 0.0542 | 0.0655 |
SMAPE | 0.151 | 0.188 | 0.273 | 0.146 | 0.150 | 0.176 | 0.0715 | 0.0546 | 0.0666 |
L1 | 0.0964 | 0.152 | 0.204 | 0.0938 | 0.0929 | 0.144 | 0.0530 | 0.0409 | 0.0432 |
MRSE | 0.0332 | 0.0557 | 0.109 | 0.0316 | 0.0331 | 0.0500 | 8.89e−3 | 4.87e−3 | 6.71e−3 |
L2 | 6.84e−3 | 0.0124 | 0.0222 | 6.47e−3 | 6.83e−3 | 0.0110 | 2.08e−3 | 1.12e−3 | 1.47e−3 |
1-SSIM | 0.571 | 0.638 | 0.737 | 0.559 | 0.567 | 0.620 | 0.301 | 0.212 | 0.272 |
(c) Disney Research