Stochastic Gradient Estimation for Higher-Order Differentiable Rendering

Zican Wang; Michael Fischer; Tobias Ritschel

ICCV 2025poster0 citations

Stochastic Gradient Estimation for Higher-Order Differentiable Rendering

Zican Wang, Michael Fischer, Tobias Ritschel

Abstract

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 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.

BibTeX

@InProceedings{Wang_2025_ICCV,
    author    = {Wang, Zican and Fischer, Michael and Ritschel, Tobias},
    title     = {Stochastic Gradient Estimation for Higher-Order Differentiable Rendering},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {28198-28206}
}