Compactly supported detail field for high quality neural implicit surfaces
Computer Graphics Forum · 13.08.2026
DOI: 10.1111/cgf.70526 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 13.08.2026. Verfasst von Guillaume Coiffier und 1 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Neural implicit surfaces are a powerful tool for encoding a surface as the zero level set of a neural function. Trained using gradient‐descent based optimizers, these methods however suffer from a low‐frequency bias that prevents them to fit fine details of the surface. Solutions to break this bias exist but often damage the regularity of the long range implicit function, making geometrical queries more difficult. In this work, we combine a 1‐Lipschitz neural function with a detail field made of compactly supported radial basis functions. While the neural function handles long‐range queries with low surface accuracy, the detail field is fitted to perturb the neural function so that its zero level set precisely goes through sampled points of the surface and locally accounts for small‐scale details. As it is compactly supported, regions where the 1‐Lipschitz property breaks are finely controlled. We therefore achieve the best of both worlds by greatly increasing the representation power of the implicit function near the zero level set while maintaining robustness far from the zero level set.
Zitieren
APA
Coiffier, G., & Basselin, J. (2026). Compactly supported detail field for high quality neural implicit surfaces. Computer Graphics Forum. https://doi.org/10.1111/cgf.70526
Vancouver
Coiffier G, Basselin J. Compactly supported detail field for high quality neural implicit surfaces. Computer Graphics Forum. 2026. doi:10.1111/cgf.70526
BibTeX
@article{Coiffier2026,
author = {Coiffier, Guillaume and Basselin, Justine},
title = {Compactly supported detail field for high quality neural implicit surfaces},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70526}
}
EUVIMED