Name
Abstract | ||
|---|---|---|
We present Optimised Path Space Regularisation (OPSR), a novel regularisation technique for forward path tracing algorithms. Our regularisation controls the amount of roughness added to materials depending on the type of sampled paths and trades a small error in the estimator for a drastic reduction of variance in difficult paths, including indirectly visible caustics. We formulate the problem as a joint bias-variance minimisation problem and use differentiable rendering to optimise our model. The learnt parameters generalise to a large variety of scenes irrespective of their geometric complexity. The regularisation added to the underlying light transport algorithm naturally allows us to handle the problem of near-specular and glossy path chains robustly. Our method consistently improves the convergence of path tracing estimators, including state-of-the-art path guiding techniques where it enables finding otherwise hard-to-sample paths and thus, in turn, can significantly speed up the learning of guiding distributions. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1111/cgf.14347 | COMPUTER GRAPHICS FORUM |
DocType | Volume | Issue |
Conference | 40 | 4 |
ISSN | Citations | PageRank |
0167-7055 | 0 | 0.34 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Philippe Weier | 1 | 0 | 0.34 |
| Marc Droske | 2 | 194 | 12.12 |
| Johannes Hanika | 3 | 297 | 25.09 |
| Andrea Weidlich | 4 | 96 | 11.48 |
| Jirí Vorba | 5 | 0 | 0.34 |