EUVIMEDEUVIMED entdecken
Crossref

Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views

Haida Feng, Hao Wei, Zewen Xu, Haolin Wang, Chade Li, Yihong Wu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3912-3920

DOI: 10.1609/aaai.v40i5.37393 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Haida Feng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, large language models (LLMs) have been explored widely for 3D scene understanding. Among them, training-free approaches are gaining attention for their flexibility and generalization over training-based methods. However, they typically struggle with accuracy and efficiency in practical deployment. To address the problems, we propose Sparse3DPR, a novel training-free framework for open-ended scene understanding, which leverages the reasoning capabilities of pre-trained LLMs and requires only sparse-view RGB inputs. Specifically, we introduce a hierarchical plane-enhanced scene graph that supports open vocabulary and adopts dominant planar structures as spatial anchors, which enables clearer reasoning chains and more reliable high-level inferences. Furthermore, we design a task-adaptive subgraph extraction method to filter query-irrelevant information dynamically, reducing contextual noise and improving 3D scene reasoning efficiency and accuracy. Experimental results demonstrate the superiority of Sparse3DPR, which achieves a 28.7% EM@1 improvement and a 78.2% speedup compared with ConceptGraphs on the Space3D-Bench. Moreover, Sparse3DPR obtains comparable performance to training-based methods on ScanQA, with additional real-world experiments confirming its robustness and generalization capability.

Zitieren

APA

Feng, H., Wei, H., Xu, Z., Wang, H., Li, C., & Wu, Y. (2026). Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3912-3920. https://doi.org/10.1609/aaai.v40i5.37393

Vancouver

Feng H, Wei H, Xu Z, Wang H, Li C, Wu Y. Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3912-3920. doi:10.1609/aaai.v40i5.37393

BibTeX
@article{Feng2026,
  author = {Feng, Haida and Wei, Hao and Xu, Zewen and Wang, Haolin and Li, Chade and Wu, Yihong},
  title = {Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3912--3920},
  doi = {10.1609/aaai.v40i5.37393}
}
Kostenlos starten →