EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GLU-Net: Global–Local Fusion Network for Event-Based Monocular Depth Estimation via Uncertainty Optimization

Shangjie Wu, Jihua Zhu, Zhikuan Zhou, Siqi Li, Shaoyi Du, Yue Gao

ACM Transactions on Multimedia Computing, Communications, and Applications · 30.06.2026 · 22 (6) · 1-20

DOI: 10.1145/3803017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 21.05.2026. Verfasst von Shangjie Wu und 5 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Natural Science Basis Research Plan in Shaanxi Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Event-based monocular depth estimation is crucial for applications such as autonomous driving, obstacle avoidance, and navigation under high-speed scenarios. Events exhibit a unique and irregular modality. To adapt them to neural networks, some studies convert event streams into event voxels or other frame-like representations. However, these approaches tend to lose the temporal characteristics of events. In this study, we propose a network that aggregates global voxel and per-channel temporal local features of event voxels across the temporal dimension, explicitly extracting events’ temporal information. Furthermore, as noise in events can interfere with the training process and is more difficult to predict than that in images, we utilize the uncertainty estimation module to mitigate the impact of uncertain factors and enhance the robustness of the model. Additionally, we employ multi-level depth features for supervisory training, which improves prediction performance compared to methods relying solely on ground-truth depth supervision. Experiments on open source datasets demonstrate the effectiveness of the proposed method. Our code can be found at https://github.com/WuShangjie/GLUNET .

Förderung

  • China Postdoctoral Science Foundation
  • Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University
  • Natural Science Basis Research Plan in Shaanxi Province of China
  • Technology Innovation Leading Program of Shaanxi

Zitieren

APA

Wu, S., Zhu, J., Zhou, Z., Li, S., Du, S., & Gao, Y. (2026). GLU-Net: Global–Local Fusion Network for Event-Based Monocular Depth Estimation via Uncertainty Optimization. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(6), 1-20. https://doi.org/10.1145/3803017

Vancouver

Wu S, Zhu J, Zhou Z, Li S, Du S, Gao Y. GLU-Net: Global–Local Fusion Network for Event-Based Monocular Depth Estimation via Uncertainty Optimization. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(6):1-20. doi:10.1145/3803017

BibTeX
@article{Wu2026,
  author = {Wu, Shangjie and Zhu, Jihua and Zhou, Zhikuan and Li, Siqi and Du, Shaoyi and Gao, Yue},
  title = {GLU-Net: Global–Local Fusion Network for Event-Based Monocular Depth Estimation via Uncertainty Optimization},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {6},
  pages = {1--20},
  doi = {10.1145/3803017}
}
Kostenlos starten →