FC-TrackNet: Fast Convergence Net for 6d Pose Tracking in Synthetic Domains

Di Jia, Qian Wang, Jun Cao, Peng Cai, Zhiyang Jin

AAAI 2023 pp. 16455-16457

doi:10.1609/AAAI.V37I13.27077 /aaai/2023/jia2023aaai-fc/

Abstract

In this work, we propose a fast convergence track net, or FC-TrackNet, based on a synthetic data-driven approach to maintaining long-term 6D pose tracking. Comparison experiments are performed on two different datasets, The results demonstrate that our approach can achieve a consistent tracking frequency of 90.9 Hz as well as higher accuracy than the state-of-the art approaches.

PDF AAAI Semantic Scholar

Cite

Text

Jia et al. "FC-TrackNet: Fast Convergence Net for 6d Pose Tracking in Synthetic Domains." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27077

Markdown

[Jia et al. "FC-TrackNet: Fast Convergence Net for 6d Pose Tracking in Synthetic Domains." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/jia2023aaai-fc/) doi:10.1609/AAAI.V37I13.27077

BibTeX

@inproceedings{jia2023aaai-fc,
  title     = {{FC-TrackNet: Fast Convergence Net for 6d Pose Tracking in Synthetic Domains}},
  author    = {Jia, Di and Wang, Qian and Cao, Jun and Cai, Peng and Jin, Zhiyang},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16455-16457},
  doi       = {10.1609/AAAI.V37I13.27077},
  url       = {https://mlanthology.org/aaai/2023/jia2023aaai-fc/}
}