Camera pose estimation in multi-view environments: From virtual scenarios to the real world

作者：

Highlights：

• A domain adaptation strategy to efficiently train network architectures

• Multi-view scenarios to estimate the relative camera pose

• Transferring learned knowledge from virtual to real world

• Evaluation of similarity of the scenarios and pose of the camera

• Experimental results on six synthetic image datasets

摘要

•A domain adaptation strategy to efficiently train network architectures•Multi-view scenarios to estimate the relative camera pose•Transferring learned knowledge from virtual to real world•Evaluation of similarity of the scenarios and pose of the camera•Experimental results on six synthetic image datasets

论文关键词：Relative camera pose estimation,Domain adaptation,Siamese architecture,Synthetic data,Multi-view environments

论文评审过程：Received 30 August 2020, Revised 5 February 2021, Accepted 3 April 2021, Available online 17 April 2021, Version of Record 22 April 2021.

论文官网地址：https://doi.org/10.1016/j.imavis.2021.104182