EUVIMEDEUVIMED entdecken
Crossref

OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding

Youjun Zhao, Jiaying Lin, Shuquan Ye, Qianshi Pang, Rynson W. H. Lau

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13289-13296

DOI: 10.1609/aaai.v40i16.38331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Youjun Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-vocabulary 3D scene understanding (OV-3D) aims to localize and classify novel objects beyond the closed set of object classes. However, existing approaches and benchmarks primarily focus on the open vocabulary problem within the context of object classes, which is insufficient in providing a holistic evaluation to what extent a model understands the 3D scene. In this paper, we introduce a more challenging task called Generalized Open-Vocabulary 3D Scene Understanding (GOV-3D) to explore the open vocabulary problem beyond object classes. It encompasses an open and diverse set of generalized knowledge, expressed as linguistic queries of fine-grained and object-specific attributes. To this end, we contribute a new benchmark named OpenScan, which consists of 3D object attributes across eight representative linguistic aspects, including affordance, property, and material. We further evaluate state-of-the-art OV-3D methods on our OpenScan benchmark and discover that these methods struggle to comprehend the abstract vocabularies of the GOV-3D task, a challenge that cannot be addressed simply by scaling up object classes during training. We highlight the limitations of existing methodologies and explore promising directions to overcome the identified shortcomings.

Zitieren

APA

Zhao, Y., Lin, J., Ye, S., Pang, Q., & Lau, R. W. H. (2026). OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13289-13296. https://doi.org/10.1609/aaai.v40i16.38331

Vancouver

Zhao Y, Lin J, Ye S, Pang Q, Lau RWH. OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13289-13296. doi:10.1609/aaai.v40i16.38331

BibTeX
@article{Zhao2026,
  author = {Zhao, Youjun and Lin, Jiaying and Ye, Shuquan and Pang, Qianshi and Lau, Rynson W. H.},
  title = {OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {16},
  pages = {13289--13296},
  doi = {10.1609/aaai.v40i16.38331}
}
Kostenlos starten →