Skip to yearly menu bar Skip to main content


Poster

Stochastic Gradient Estimation for Higher-Order Differentiable Rendering

Zican Wang · Michael Fischer · Tobias Ritschel

Exhibit Hall I #2610
Highlight Award Highlight
[ ] [ Project Page ]
Thu 23 Oct 5:45 p.m. PDT — 7:45 p.m. PDT

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.

Live content is unavailable. Log in and register to view live content