EUVIMEDEUVIMED entdecken
Crossref

TRO-VO: Transformers for Feature Refinement and Pose Optimization in Monocular Visual Odometry

Zhen Li, Yidian Huang, Haikuo Liu, Fang Deng, Jingou Zhang, Samson Shenglong Yu, Peng Shi

IEEE Transactions on Intelligent Transportation Systems · 2026-11 · 27 (11) · 14335-14347

DOI: 10.1109/tits.2026.3723848 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-11. Verfasst von Zhen Li und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monocular visual odometry based on self-supervised learning enables autonomous vehicles to estimate precise self-motion in challenging environments without stable satellite signals. To address the accumulated error typically associated with the limited receptive field of monocular setups, our proposed method, named transformers for feature refinement and pose optimization in monocular visual odometry (TRO-VO), integrates learning-based pose prediction, motion feature refinement, and pose graph optimization using transformer-based networks. In the first stage, TRO-VO extracts feature-level changes in the Deformable Pose Former (DPF), revealing the relationship between two consecutive images. Subsequently, a Pose Graph Former (PGF) is devised to optimize the predicted motions and refine the feature maps. A graph-based pose consistency loss function is used to enforce geometric consistency in the optimized motions. Furthermore, TRO-VO enforces separate pose predictions from the DPF and PGF modules: coarse-level perception from DPF and fine-level refinement from PGF, thereby enhancing the interpretability of the entire pipeline. Experimental results on KITTI, RobotCar datasets, as well as self-collected outdoor data demonstrate the performance and generalization capabilities of TRO-VO.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Huang, Y., Liu, H., Deng, F., Zhang, J., Yu, S. S., & Shi, P. (2026). TRO-VO: Transformers for Feature Refinement and Pose Optimization in Monocular Visual Odometry. IEEE Transactions on Intelligent Transportation Systems, 27(11), 14335-14347. https://doi.org/10.1109/tits.2026.3723848

Vancouver

Li Z, Huang Y, Liu H, Deng F, Zhang J, Yu SS, et al. TRO-VO: Transformers for Feature Refinement and Pose Optimization in Monocular Visual Odometry. IEEE Transactions on Intelligent Transportation Systems. 2026;27(11):14335-14347. doi:10.1109/tits.2026.3723848

BibTeX
@article{Li2026,
  author = {Li, Zhen and Huang, Yidian and Liu, Haikuo and Deng, Fang and Zhang, Jingou and Yu, Samson Shenglong and Shi, Peng},
  title = {TRO-VO: Transformers for Feature Refinement and Pose Optimization in Monocular Visual Odometry},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2026},
  volume = {27},
  number = {11},
  pages = {14335--14347},
  doi = {10.1109/tits.2026.3723848}
}
Kostenlos starten →