Stochastic Gradient Estimation for Higher-order Differentiable Rendering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908479567953920 |
|---|---|
| author | Wang, Zican Fischer, Michael Ritschel, Tobias |
| author_facet | Wang, Zican Fischer, Michael Ritschel, Tobias |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03489 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Stochastic Gradient Estimation for Higher-order Differentiable Rendering Wang, Zican Fischer, Michael Ritschel, Tobias Graphics 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. |
| title | Stochastic Gradient Estimation for Higher-order Differentiable Rendering |
| topic | Graphics |
| url | https://arxiv.org/abs/2412.03489 |