Efficient Path-Space Differentiable Volume Rendering With Respect To Shapes
Zihan Yu1,2, Cheng Zhang2, Olivier Maury2, Christophe Hery2, Zhao Dong2, and Shuang Zhao1
1University of California, Irvine          2Meta Reality Labs Research
Computer Graphics Forum (EGSR 2023), 42(4), 2023
teaser
Abstract

Differentiable rendering of translucent objects with respect to their shapes has been a long-standing problem. State-of-the- art methods require detecting object silhouettes or specifying change rates inside translucent objects—both of which can be expensive for translucent objects with complex shapes.

In this paper, we address this problem for translucent objects with no refractive or reflective boundaries. By reparameterizing interior components of differential path integrals, our new formulation does not require change rates to be specified in the interior of objects. Further, we introduce new Monte Carlo estimators based on this formulation that do not require explicit detection of object silhouettes.

Downloads
  • Paper: pdf (6 MB)
Bibtex citation
@article{Yu:2023:PSDR-Vol2,
  title={Efficient Path-Space Differentiable Volume Rendering With Respect To Shapes},
  author={Yu, Z. and Zhang, C. and Maury, O. and Hery, C. and Dong, Z. and Zhao, S.},
  journal={Computer Graphics Forum},
  volume={42},
  number={4},
  year={2023}
}
Acknowledgments

We thank the anonymous reviewers for their constructive feedback. This work was supported in part by NSF grant 1900927.