Differentiable Shadow Mapping for Efficient Inverse Graphics

TU Berlin

CVPR 2023

Abstract

We show how shadows can be efficiently generated in differentiable rendering of triangle meshes. Our central observation is that pre-filtered shadow mapping, a technique for approximating shadows based on rendering from the perspective of a light, can be combined with existing differentiable rasterizers to yield differentiable visibility information. We demonstrate at several inverse graphics problems that differentiable shadow maps are orders of magnitude faster than differentiable light transport simulation with similar accuracy -- while differentiable rasterization without shadows often fails to converge.

Video

BibTeX

@InProceedings{worchel:2023:diff_shadow_mapping,
      author    = {Worchel, Markus and Alexa, Marc},
      title     = {Differentiable Shadow Mapping for Efficient Inverse Graphics},
      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      month     = {June},
      year      = {2023},
      pages     = {142-153}
  }

Acknowledgements

We thank the authors of the 3D models used in our work: Spot by Keenan Crane, Utah Teapot by Martin Newell, Bunny and Armadillo by Stanford Computer Graphics Laboratory. Thanks to the authors of Nerfies for providing this project page template.