arXiv Open Access 2024

Stochastic Gradient Estimation for Higher-order Differentiable Rendering

Zican Wang Michael Fischer Tobias Ritschel

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.GR

Penulis (3)

Zican Wang

Michael Fischer

Tobias Ritschel

Format Sitasi

APA MLA BibTeX

Wang, Z., Fischer, M., Ritschel, T. (2024). Stochastic Gradient Estimation for Higher-order Differentiable Rendering. https://arxiv.org/abs/2412.03489

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓