This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras. The proposed network takes RGB images from both cameras as input and directly produces the relative rotation and translation as output. The system is trained in an end-to-end manner utilising transfer learning from a large scale classification dataset. The introduced approach is compared with widely used local feature based methods (SURF, ORB) and the results indicate a clear improvement over the baseline. In addition, a variant of the proposed architecture containing a spatial pyramid pooling (SPP) layer is evaluated and shown to further improve the performance.
@article{arxiv.1702.01381,
title = {Relative Camera Pose Estimation Using Convolutional Neural Networks},
author = {Iaroslav Melekhov and Juha Ylioinas and Juho Kannala and Esa Rahtu},
journal= {arXiv preprint arXiv:1702.01381},
year = {2017}
}
Comments
To be published in proceedings of Advanced Concepts for Intelligent Vision Systems (ACIVS) 2017