Basis Networks: Learning basis functions for free‐form triangulations
Computer Graphics Forum · 10.04.2026
DOI: 10.1111/cgf.70326 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 10.04.2026. Verfasst von T. Djuren und 1 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 European Research Council.
Abstract (Originalsprache)
We present a framework for learning compactly supported basis functions that define tangent continuous surfaces based on coarse irregular triangle meshes. The basis functions are represented as MLPs. Smoothness of the basis functions is achieved by using the values of Loop basis functions as the parameterization of the surface. Post‐multiplying the value of the MLP with the Loop basis yields smooth compact support. We show that this approach works similar or better than Neural Subdivision in terms of recreating given geometry, while the runtime scales better with surface resolution and can be evaluated at arbitrary resolution.
Förderung
- H2020 European Research Council
Zitieren
APA
Djuren, T., & Alexa, M. (2026). Basis Networks: Learning basis functions for free‐form triangulations. Computer Graphics Forum. https://doi.org/10.1111/cgf.70326
Vancouver
Djuren T, Alexa M. Basis Networks: Learning basis functions for free‐form triangulations. Computer Graphics Forum. 2026. doi:10.1111/cgf.70326
BibTeX
@article{Djuren2026,
author = {Djuren, T. and Alexa, M.},
title = {Basis Networks: Learning basis functions for free‐form triangulations},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70326}
}
EUVIMED