EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation

Zhe Zhu, Yiheng Zhang, Peng Li, Zixing Zhao, Honghua Chen, Yaqing Zhang, Le Wan, Zhiyang Dou, Cheng Lin, Yuan Liu, Mingqiang Wei, Wenping Wang

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-17

DOI: 10.1145/3842577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Zhe Zhu und 11 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies, but existing approaches typically only address a specific setting, such as text-guided part segmentation or point-based interaction. In this work, we argue that these settings can be unified as an intent-conditioned generative problem, where different prompts specify the desired part decomposition. To this end, we introduce PartLLM, a unified multimodal model that formulates 3D part segmentation as autoregressive semantic decomposition. Conditioned on an input shape and a user prompt, PartLLM autoregressively generates semantic part hypotheses as queries for mask prediction and feeds them to a decomposition-aware decoder that jointly predicts coherent part masks. This unified design supports text-guided part segmentation, interactive segmentation, and full-shape semantic decomposition with controllable granularity within a single model. Extensive experiments across these task settings show that PartLLM consistently outperforms task-specific baselines, demonstrating the effectiveness of unifying 3D part segmentation under an intent-conditioned generative formulation. Code and data for this paper are available at https://github.com/czvvd/PartLLM.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhu, Z., Zhang, Y., Li, P., Zhao, Z., Chen, H., Zhang, Y., Wan, L., Dou, Z., Lin, C., Liu, Y., Wei, M., & Wang, W. (2026). PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation. ACM Transactions on Graphics, 45(6), 1-17. https://doi.org/10.1145/3842577

Vancouver

Zhu Z, Zhang Y, Li P, Zhao Z, Chen H, Zhang Y, et al. PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation. ACM Transactions on Graphics. 2026;45(6):1-17. doi:10.1145/3842577

BibTeX
@article{Zhu2026,
  author = {Zhu, Zhe and Zhang, Yiheng and Li, Peng and Zhao, Zixing and Chen, Honghua and Zhang, Yaqing and Wan, Le and Dou, Zhiyang and Lin, Cheng and Liu, Yuan and Wei, Mingqiang and Wang, Wenping},
  title = {PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--17},
  doi = {10.1145/3842577}
}
Kostenlos starten →