Stochastic Gradient Estimation for Higher-Order Differentiable Rendering

Zican Wang, Michael Fischer, Tobias Ritschel; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025, pp. 28198-28206

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.

Related Material

[pdf] [supp] [arXiv]
[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} }