Fischer, Michael;
Ritschel, Tobias;
(2023)
Plateau-reduced Differentiable Path Tracing.
In:
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
(pp. pp. 4285-4294).
IEEE
Preview |
Text
2211.17263v2.pdf - Accepted Version Download (13MB) | Preview |
Abstract
Current differentiable renderers provide light transport gradients with respect to arbitrary scene parameters. However, the mere existence of these gradients does not guarantee useful update steps in an optimization. Instead, inverse rendering might not converge due to inherent plateaus, i.e., regions of zero gradient, in the objective function. We propose to alleviate this by convolving the high-dimensional rendering function, that maps scene parameters to images, with an additional kernel that blurs the parameter space. We describe two Monte Carlo estimators to compute plateau-reduced gradients efficiently, i.e., with low variance, and show that these translate into net-gains in optimization error and runtime performance. Our approach is a straightforward extension to both black-box and differentiable renderers and enables optimization of problems with intricate light transport, such as caustics or global illumination, that existing differentiable renderers do not converge on. Our code is at github.com/mfischerucl/prdpt.
| Type: | Proceedings paper |
|---|---|
| Title: | Plateau-reduced Differentiable Path Tracing |
| Event: | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Location: | CANADA, Vancouver |
| Dates: | 17 Jun 2023 - 24 Jun 2023 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/CVPR52729.2023.00417 |
| Publisher version: | https://doi.org/10.1109/CVPR52729.2023.00417 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Metalearning, Smoothing methods, Runtime, Monte Carlo methods, Rendering (computer graphics), Pattern recognition, Noise measurement |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10192087 |
Archive Staff Only
 |
View Item |
