EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation

Peiyu Xu, Lifan Wu, Benedikt Bitterli, Ravi Ramamoorthi, Shuang Zhao

ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-12

DOI: 10.1145/3811325 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Peiyu Xu und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To enable differentiation with respect to object geometries, boundary path integrals—central to physics-based differentiable rendering—must be estimated numerically. Although their mathematical formulation is well established, designing efficient and robust numerical estimators remains challenging. Most state-of-the-art boundary sampling methods rely on primary-sample-space guiding, which tends to break down on finely tessellated geometries; reparameterization-based alternatives, meanwhile, often incur high variance and/or significant computational overhead. In this paper, we introduce a simple, robust, and consistent solution to this problem. At the core of our approach is a novel formulation of the boundary integral based on kernel-density estimation. Much like photon mapping, we slightly expand the measure-zero domain of integration with a kernel, sidestepping the need to sample directly on a delta-function region in path space. To our knowledge, this is the first such application of kernel-density methods for boundary integral evaluation. We validate our method by comparing its derivative estimates against finite differences (FD), and further demonstrate its practical utility by benchmarking against several state-of-the-art baselines in synthetic inverse-rendering scenarios.

Förderung

  • NSF

Zitieren

APA

Xu, P., Wu, L., Bitterli, B., Ramamoorthi, R., & Zhao, S. (2026). Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation. ACM Transactions on Graphics, 45(4), 1-12. https://doi.org/10.1145/3811325

Vancouver

Xu P, Wu L, Bitterli B, Ramamoorthi R, Zhao S. Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation. ACM Transactions on Graphics. 2026;45(4):1-12. doi:10.1145/3811325

BibTeX
@article{Xu2026,
  author = {Xu, Peiyu and Wu, Lifan and Bitterli, Benedikt and Ramamoorthi, Ravi and Zhao, Shuang},
  title = {Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {4},
  pages = {1--12},
  doi = {10.1145/3811325}
}
Kostenlos starten →