English

Differentiable Shadow Mapping for Efficient Inverse Graphics

Graphics 2023-08-22 v1 Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.2308.10896,
  title  = {Differentiable Shadow Mapping for Efficient Inverse Graphics},
  author = {Markus Worchel and Marc Alexa},
  journal= {arXiv preprint arXiv:2308.10896},
  year   = {2023}
}

Comments

CVPR 2023, project page: https://mworchel.github.io/differentiable-shadow-mapping

R2 v1 2026-06-28T12:00:42.079Z