Physics-Based Inverse Rendering using
Combined Implicit and Explicit Geometries
Guangyan Cai1,2, Kai Yan1,2, Zhao Dong2, Ioannis Gkioulekas3, and Shuang Zhao1
1University of California, Irvine          2Meta Reality Labs Research          3Carnegie Mellon University
Computer Graphics Forum (EGSR 2022), 41(4), 2022

Mathematically representing the shape of an object is a key ingredient for solving inverse rendering problems. Explicit representations like meshes are efficient to render in a differentiable fashion but have difficulties handling topology changes. Implicit representations like signed-distance functions, on the other hand, offer better support of topology changes but are much more difficult to use for physics-based differentiable rendering. We introduce a new physics-based inverse rendering pipeline that uses both implicit and explicit representations. Our technique enjoys the benefit of both representations by supporting both topology changes and differentiable rendering of complex effects such as environmental illumination, soft shadows, and interreflection. We demonstrate the effectiveness of our technique using several synthetic and real examples.

  • Paper: pdf (14 MB)
  • Supplemental material: pdf (26 MB)
  • Code & data: zip (118 MB)
Bibtex citation
  title={Physics-Based Inverse Rendering using Combined Implicit and Explicit Geometries},
  author={Cai, G. and Yan, K. and Dong, Z. and Gkioulekas, I. and Zhao, S.},
  journal={Computer Graphics Forum},

We thank the anonymous reviewers for their constructive feedback. This work was supported in part by NSF grants 1900783, 1900849, and 1900927. Ioannis Gkioulekas was supported by a Sloan Research Fellowship.