Moment Bounds are Differentiable:
Efficiently Approximating Measures in Inverse Rendering

ACM Transactions on Graphics (SIGGRAPH 2025)
Markus Worchel · Marc Alexa

About

This repository contains the official implementation of the paper "Moment Bounds are Differentiable: Efficiently Approximating Measures in Inverse Rendering"

Coming soon

License and Copyright

The code in this repository is provided under a 3-clause BSD license.

Citation

If you find this code or our method useful for your research, please cite our paper

@article{worchel:2025:diffmoments,
author = {Worchel, Markus and Alexa, Marc},
title = {Moment Bounds are Differentiable: Efficiently Approximating Measures in Inverse Rendering},
year = {2025},
issue_date = {August 2025},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {44},
number = {4},
issn = {0730-0301},
url = {https://doi.org/10.1145/3730899},
doi = {10.1145/3730899},
journal = {ACM Trans. Graph.},
month = jul,
articleno = {80},
numpages = {21},
keywords = {differentiable rendering, shadows}
}