SegviGen: Repurposing 3D Generative Model for Part Segmentation
ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-12
DOI: 10.1145/3811399 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Lin Li und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 88 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
We introduce SegviGen , a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suffering from cross-view inconsistency and blurred boundaries, or explore native 3D discriminative segmentation, which typically requires large-scale annotated 3D data and substantial training resources. In contrast, SegviGen leverages the structured priors encoded in pretrained 3D generative model to induce segmentation through distinctive part colorization, establishing a novel and efficient framework for part segmentation. Specifically, SegviGen encodes an input 3D asset and predicts part-indicative colors on active voxels of a geometry-aligned reconstruction. It supports interactive part segmentation, full segmentation, and full segmentation with 2D guidance in a unified framework. Extensive experiments show that SegviGen improves over the prior state of the art by 40% on interactive part segmentation and by 15% on full segmentation, while using only 0.32% of the training data. This undoubtedly demonstrates that pretrained 3D generative priors transfer effectively to 3D part segmentation, enabling strong performance with limited supervision. Code and pretrained weights are publicly available at https://github.com/Nelipot-Lee/SegviGen.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, L., Feng, H., Huang, Z., Chen, H., Nie, W., Hou, S., Fan, K., Hu, P., Wang, S., Li, B., & Sheng, L. (2026). SegviGen: Repurposing 3D Generative Model for Part Segmentation. ACM Transactions on Graphics, 45(4), 1-12. https://doi.org/10.1145/3811399
Vancouver
Li L, Feng H, Huang Z, Chen H, Nie W, Hou S, et al. SegviGen: Repurposing 3D Generative Model for Part Segmentation. ACM Transactions on Graphics. 2026;45(4):1-12. doi:10.1145/3811399
BibTeX
@article{Li2026,
author = {Li, Lin and Feng, Haoran and Huang, Zehuan and Chen, Haohua and Nie, Wenbo and Hou, Shaohua and Fan, Keqing and Hu, Pan and Wang, Sheng and Li, Buyu and Sheng, Lu},
title = {SegviGen: Repurposing 3D Generative Model for Part Segmentation},
journal = {ACM Transactions on Graphics},
year = {2026},
volume = {45},
number = {4},
pages = {1--12},
doi = {10.1145/3811399}
}
EUVIMED