EUVIMEDEUVIMED entdecken
Crossref

Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning

Yu Fei, Quan Deng, Shengeng Tang, Li Yuehua, Lechao Cheng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3894-3902

DOI: 10.1609/aaai.v40i5.37391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yu Fei und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-world 3D scene understanding is fundamentally challenging for vision and robotics, due to the constraints of closed-vocabulary supervision and static annotations. To address this, we propose a unified framework for Open-World 3D Scene Graph Generation with Retrieval-Augmented Reasoning, which enables generalizable and interactive 3D scene understanding. Our method integrates vision-language models with retrieval-based reasoning to support multimodal exploration and language-guided interaction. The framework comprises two key components: (1) a dynamic scene graph generation module that detects objects and infers semantic relationships without fixed label sets, and (2) a retrieval-augmented reasoning pipeline that encodes scene graphs into a vector database to support text/image-conditioned queries. We evaluate our method on 3DSSG and Replica benchmarks across four tasks—scene question answering, visual grounding, instance retrieval, and task planning—demonstrating robust generalization and superior performance in diverse environments. Our results highlight the effectiveness of combining open-vocabulary perception with retrieval-based reasoning for scalable 3D scene understanding.

Zitieren

APA

Fei, Y., Deng, Q., Tang, S., Yuehua, L., & Cheng, L. (2026). Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3894-3902. https://doi.org/10.1609/aaai.v40i5.37391

Vancouver

Fei Y, Deng Q, Tang S, Yuehua L, Cheng L. Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3894-3902. doi:10.1609/aaai.v40i5.37391

BibTeX
@article{Fei2026,
  author = {Fei, Yu and Deng, Quan and Tang, Shengeng and Yuehua, Li and Cheng, Lechao},
  title = {Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3894--3902},
  doi = {10.1609/aaai.v40i5.37391}
}
Kostenlos starten →