EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Text2MFN and MFPredictor: Text-Conditioned Mesh Face-Count Recommendation for Efficient 3D Generation

Bingyang Ji, Shan Cui

Applied Sciences · 03.08.2026 · 16 (15) · 7722

DOI: 10.3390/app16157722 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 03.08.2026. Verfasst von Bingyang Ji und 1 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current text-to-3D methods primarily improve geometric fidelity, topology, and generation efficiency, but generally require mesh complexity to be determined indirectly by architecture, sequence length, user settings, or post-processing. We formulate text-conditioned mesh face-count recommendation as a regression task that predicts a practical triangular-face budget from the object category, silhouette, semantic parts, structural relationships, and geometry-related details expressed in a prompt. We construct Text2MFN, a synthetic dataset containing 1,000,000 text–face-count pairs, and propose MFPredictor, a lightweight dual-branch model that separates semantic context from geometry-related complexity cues and combines them through bidirectional calibration, gated fusion, a small mixture-of-experts module, and residual regression. All models are trained exclusively on Text2MFN and evaluated on its held-out test set and on an independent benchmark containing 200,000 QEM-derived multi-LOD records from 40,000 Objaverse meshes. MFPredictor obtains a MAPE of 4.38% and a ±20% accuracy of 95.45% on Text2MFN, and a MAPE of 7.96% and a ±20% accuracy of 86.41% on the Objaverse-based benchmark. With 481,275 parameters and a measured average regression latency of 2.09 ms, the model provides an efficient front-end prediction of mesh complexity. The real-mesh results demonstrate transfer under the evaluated Text2MFN-to-Objaverse/QEM protocol and define the validated scope of the reported generalization.

Zitieren

APA

Ji, B., & Cui, S. (2026). Text2MFN and MFPredictor: Text-Conditioned Mesh Face-Count Recommendation for Efficient 3D Generation. Applied Sciences, 16(15), 7722. https://doi.org/10.3390/app16157722

Vancouver

Ji B, Cui S. Text2MFN and MFPredictor: Text-Conditioned Mesh Face-Count Recommendation for Efficient 3D Generation. Applied Sciences. 2026;16(15):7722. doi:10.3390/app16157722

BibTeX
@article{Ji2026,
  author = {Ji, Bingyang and Cui, Shan},
  title = {Text2MFN and MFPredictor: Text-Conditioned Mesh Face-Count Recommendation for Efficient 3D Generation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7722},
  doi = {10.3390/app16157722}
}
Kostenlos starten →