EUVIMEDEUVIMED entdecken
Crossref

Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model

Weilin Sun, Xinran Li, Manyi Li, Kai Xu, Xiangxu Meng, Lei Meng

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (7) · 7122-7130

DOI: 10.1609/aaai.v39i7.32765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Weilin Sun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Indoor scene synthesis aims to automatically produce plausible, realistic, and diverse 3D indoor scenes, especially given arbitrary user requirements. Recently, the promising generalization ability of pre-trained large language models (LLM) assist in open-vocabulary indoor scene synthesis. However, the challenge lies in converting the LLM-generated outputs into reasonable and physically feasible scene layouts. In this paper, we propose to generate hierarchically structured scene descriptions with LLM and then compute the scene layouts. Specifically, we train a hierarchy-aware network to infer the fine-grained relative positions between objects and design a divide-and-conquer optimization to solve for scene layouts. The advantages of using hierarchically structured scene representation are two-fold. First, the hierarchical structure provides a rough grounding for object arrangement, which alleviates contradictory placements with dense relations and enhances the generalization ability of the network to infer fine-grained placements. Second, it naturally supports the divide-and-conquer optimization, by first arranging the sub-scenes and then the entire scene, to more effectively solve for a feasible layout. We conduct extensive comparison experiments and ablation studies with both qualitative and quantitative evaluations to validate the effectiveness of our key designs with the hierarchically structured scene representation. Our approach can generate more reasonable scene layouts while better aligned with the user requirements and LLM descriptions. We also present open-vocabulary scene synthesis and interactive scene design results to show the strength of our approach in the applications.

Zitieren

APA

Sun, W., Li, X., Li, M., Xu, K., Meng, X., & Meng, L. (2025). Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model. Proceedings of the AAAI Conference on Artificial Intelligence, 39(7), 7122-7130. https://doi.org/10.1609/aaai.v39i7.32765

Vancouver

Sun W, Li X, Li M, Xu K, Meng X, Meng L. Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(7):7122-7130. doi:10.1609/aaai.v39i7.32765

BibTeX
@article{Sun2025,
  author = {Sun, Weilin and Li, Xinran and Li, Manyi and Xu, Kai and Meng, Xiangxu and Meng, Lei},
  title = {Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {7},
  pages = {7122--7130},
  doi = {10.1609/aaai.v39i7.32765}
}
Kostenlos starten →