PoissonNet: A Local-Global Approach for Learning on Surfaces
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-16
DOI: 10.1145/3763298 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Arman Maesumi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 112 Literaturangaben. Gefördert von: NSF.
Abstract (Originalsprache)
Many network architectures exist for learning on meshes, yet their constructions entail delicate trade-offs between difficulty learning high-frequency features, insufficient receptive field, sensitivity to discretization, and inefficient computational overhead. Drawing from classic local-global approaches in mesh processing, we introduce PoissonNet, a novel neural architecture that overcomes all of these deficiencies by formulating a local-global learning scheme, which uses Poisson's equation as the primary mechanism for feature propagation. Our core network block is simple; we apply learned local feature transformations in the gradient domain of the mesh, then solve a Poisson system to propagate scalar feature updates across the surface globally. Our local-global learning framework preserves the features's full frequency spectrum and provides a truly global receptive field, while remaining agnostic to mesh triangulation. Our construction is efficient, requiring far less compute overhead than comparable methods, which enables scalability—both in the size of our datasets, and the size of individual training samples. These qualities are validated on various experiments where, compared to previous intrinsic architectures, we attain state-of-the-art performance on semantic segmentation and parameterizing highly-detailed animated surfaces. Finally, as a central application of PoissonNet, we show its ability to learn deformations, significantly outperforming state-of-the-art architectures that learn on surfaces. https://github.com/ArmanMaesumi/poissonnet
Förderung
- NSF
Zitieren
APA
Maesumi, A., Makadia, T., Groueix, T., Kim, V., Ritchie, D., & Aigerman, N. (2025). PoissonNet: A Local-Global Approach for Learning on Surfaces. ACM Transactions on Graphics, 44(6), 1-16. https://doi.org/10.1145/3763298
Vancouver
Maesumi A, Makadia T, Groueix T, Kim V, Ritchie D, Aigerman N. PoissonNet: A Local-Global Approach for Learning on Surfaces. ACM Transactions on Graphics. 2025;44(6):1-16. doi:10.1145/3763298
BibTeX
@article{Maesumi2025,
author = {Maesumi, Arman and Makadia, Tanish and Groueix, Thibault and Kim, Vladimir and Ritchie, Daniel and Aigerman, Noam},
title = {PoissonNet: A Local-Global Approach for Learning on Surfaces},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--16},
doi = {10.1145/3763298}
}
EUVIMED