EUVIMEDEUVIMED entdecken
Crossref

URTOME: An Uncertainty- and Relation-Aware Transformer for 3D Visual Grounding

Dingkun Zhu, Libo Zheng, Honghui Fan, Hechong Li, Xinlin Bu, Fu Lee Wang, Haoran Xie

ACM Transactions on Multimedia Computing, Communications, and Applications · 17.11.2026

DOI: 10.1145/3863953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 17.11.2026. Verfasst von Dingkun Zhu und 6 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D visual grounding aims to localize target objects in point-cloud scenes based on natural-language descriptions. However, incomplete geometry can hinder accurate object-center estimation, insufficient semantic cues can make target discrimination difficult, and similar objects can introduce relational ambiguity. To address these challenges, we propose URTOME, an Uncertainty- and Relation-Aware Transformer that integrates complementary geometric and linguistic modeling. Uncertainty-Aware Voting estimates point-wise voting uncertainty to refine seed-to-center offsets. Multi-Granularity Text Context Enhancement enriches language representations through implicit semantic enrichment and explicit description diversification. The Relation-Aware Transformer models directional and proximity relations among candidate objects to facilitate cross-modal matching. On ScanRefer, URTOME achieves 49.38% Acc@0.25 and 37.32% Acc@0.5, outperforming the 3DVG-Transformer baseline by 4.23 and 4.77 percentage points, respectively. It also achieves overall accuracies of 53.6% and 64.1% on Nr3D and Sr3D, respectively. Ablation studies demonstrate the complementary contributions of the three components, while proposal-level evaluation shows that uncertainty-aware voting improves proposal coverage and reduces vote-center error. These results highlight the effectiveness of integrating voting uncertainty, enriched textual context, and spatial relations for accurate 3D visual grounding.

Zitieren

APA

Zhu, D., Zheng, L., Fan, H., Li, H., Bu, X., Wang, F. L., & Xie, H. (2026). URTOME: An Uncertainty- and Relation-Aware Transformer for 3D Visual Grounding. ACM Transactions on Multimedia Computing, Communications, and Applications. https://doi.org/10.1145/3863953

Vancouver

Zhu D, Zheng L, Fan H, Li H, Bu X, Wang FL, et al. URTOME: An Uncertainty- and Relation-Aware Transformer for 3D Visual Grounding. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026. doi:10.1145/3863953

BibTeX
@article{Zhu2026,
  author = {Zhu, Dingkun and Zheng, Libo and Fan, Honghui and Li, Hechong and Bu, Xinlin and Wang, Fu Lee and Xie, Haoran},
  title = {URTOME: An Uncertainty- and Relation-Aware Transformer for 3D Visual Grounding},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  doi = {10.1145/3863953}
}
Kostenlos starten →