Practical Gaussian Process Implicit Surfaces with Sparse Convolutions
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-18
DOI: 10.1145/3763329 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Kehan Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
A fundamental challenge in rendering has been the dichotomy between surface and volume models. Gaussian Process Implicit Surfaces (GPISes) recently provided a unified approach for surfaces, volumes, and the spectrum in between. However, this representation remains impractical due to its high computational cost and mathematical complexity. We address these limitations by reformulating GPISes as procedural noise, eliminating expensive linear system solves while maintaining control over spatial correlations. Our method enables efficient sampling of stochastic realizations and supports flexible conditioning of values and derivatives through pathwise updates. To further enable practical rendering, we derive analytic distributions for surface normals, allowing for variance-reduced light transport via next-event estimation and multiple importance sampling. Our framework achieves efficient, high-quality rendering of stochastic surfaces and volumes with significantly simplified implementations on both CPU and GPU, while preserving the generality of the original GPIS representation.
Förderung
- National Science Foundation
Zitieren
APA
Xu, K., Bitterli, B., d'Eon, E., & Jarosz, W. (2025). Practical Gaussian Process Implicit Surfaces with Sparse Convolutions. ACM Transactions on Graphics, 44(6), 1-18. https://doi.org/10.1145/3763329
Vancouver
Xu K, Bitterli B, d'Eon E, Jarosz W. Practical Gaussian Process Implicit Surfaces with Sparse Convolutions. ACM Transactions on Graphics. 2025;44(6):1-18. doi:10.1145/3763329
BibTeX
@article{Xu2025,
author = {Xu, Kehan and Bitterli, Benedikt and d'Eon, Eugene and Jarosz, Wojciech},
title = {Practical Gaussian Process Implicit Surfaces with Sparse Convolutions},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--18},
doi = {10.1145/3763329}
}
EUVIMED