Layer3D: A 3D Layered Representation for Multiview Vector Graphics
Computer Graphics Forum · 14.04.2026
DOI: 10.1111/cgf.70375 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 14.04.2026. Verfasst von Zhongyue Guan und 2 weiteren Autor:innen. Die Arbeit nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
We present Layer3D, a novel 3D neural representation that models objects as collections of decomposable neural implicit primitives. These primitives enable the generation of layered images with consistent correspondences across viewpoints, establishing a flexible framework for multiview vector graphics decomposition. Integrated into a text‐to‐3D pipeline via Score Distillation Sampling (SDS), Layer3D learns to generate primitives with diverse shape topologies while preserving structural coherence. To ensure front‐to‐back ordering required for 2D flat graphics, our method incorporates front‐to‐back rendering and shape regularization constraints. Experimental results demonstrate that Layer3D consistently produces meaningful, topology‐diverse layers across multiple views, thereby facilitating intuitive and effective layer‐based vector editing.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Guan, Z., Hu, Y., & Wang, Z. (2026). Layer3D: A 3D Layered Representation for Multiview Vector Graphics. Computer Graphics Forum. https://doi.org/10.1111/cgf.70375
Vancouver
Guan Z, Hu Y, Wang Z. Layer3D: A 3D Layered Representation for Multiview Vector Graphics. Computer Graphics Forum. 2026. doi:10.1111/cgf.70375
BibTeX
@article{Guan2026,
author = {Guan, Zhongyue and Hu, Yixin and Wang, Zeyu},
title = {Layer3D: A 3D Layered Representation for Multiview Vector Graphics},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70375}
}
EUVIMED