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 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.

Interactive Demo
Coming soon!
Results

Acknowledgements
Our approach is heavily based on the PRDPT paper by Michael Fischer and Tobias Ritschel. With additional higher order optimization and sampling schemme. Please check out the original paper here.