| Autor: |
Zican, Wang, Fischer, Michael, Ritschel, Tobias |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
We derive methods to compute higher order differentials (Hessians and Hessian-vector products) of the rendering operator. Our approach is based on importance sampling of a convolution that represents the differentials of rendering parameters and shows to be applicable to both rasterization and path tracing. We further suggest an aggregate sampling strategy to importance-sample multiple dimensions of one convolution kernel simultaneously. We demonstrate that this information improves convergence when used in higher-order optimizers such as Newton or Conjugate Gradient relative to a gradient descent baseline in several inverse rendering tasks. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
