Learning-Based Gaussian Belief Propagation for Bundle Adjustment in Visual SLAM

Yu Siang Feng*, Jian Yu Chen, Han Chun Wang, Chih Wei Huang, Jann Long Chern

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

Bundle adjustment (BA) is the major optimization step simultaneously refining 3D coordinates and accounts for a large portion of execution time in visual simultaneous localization and mapping (SLAM). While the Levenberg-Marquardt (LM) based algorithms have been commonly used for fast BA, recent solutions adopting iterative and originally slow Gaussian belief propagation (GBP) show its potential to be fast and accurate on emerging computation platforms. We propose a novel architecture to predict the message passing in GBP with deep neural networks. The model generates messages several iterations ahead to significantly reduce the number of required computation loops. Also, the process converges with hyperparameter tuning and avoids the dependency of an arbitrary damping factor for GBP to be stabilized. Compared with standard GBP, the learning-based approach achieves the same level of accuracy while running 17.7 times faster under GPU acceleration.

原文英語
主出版物標題2022 IEEE GLOBECOM Workshops, GC Wkshps 2022 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面166-171
頁數6
ISBN(電子)9781665459754
DOIs
出版狀態已發佈 - 2022
事件2022 IEEE GLOBECOM Workshops, GC Wkshps 2022 - Virtual, Online, 巴西
持續時間: 2022 12月 42022 12月 8

出版系列

名字2022 IEEE GLOBECOM Workshops, GC Wkshps 2022 - Proceedings

會議

會議2022 IEEE GLOBECOM Workshops, GC Wkshps 2022
國家/地區巴西
城市Virtual, Online
期間2022/12/042022/12/08

ASJC Scopus subject areas

  • 儀器
  • 電腦網路與通信
  • 控制和優化

指紋

深入研究「Learning-Based Gaussian Belief Propagation for Bundle Adjustment in Visual SLAM」主題。共同形成了獨特的指紋。

引用此