Towards CNN Map Representation and Compression for Camera Relocalisation

Luis Contreras, Walterio Mayol-Cuevas; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 292-299

Abstract


This paper presents a study on the use of Convolutional Neural Networks for camera relocalisation and its application to map compression. We follow state of the art visual relocalisation results and evaluate the response to different data inputs. We use a CNN map representation and introduce the notion of map compression under this paradigm by using smaller CNN architectures without sacrificing relocalisation performance. We evaluate this approach in a series of publicly available datasets over a number of CNN architectures with different sizes, both in complexity and number of layers. This formulation allows us to improve relocalisation accuracy by increasing the number of training trajectories while maintaining a constant-size CNN.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Contreras_2018_CVPR_Workshops,
author = {Contreras, Luis and Mayol-Cuevas, Walterio},
title = {Towards CNN Map Representation and Compression for Camera Relocalisation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}