VidLoc: 6-DoF Video-Clip Relocalization

@article{Clark2017VidLoc6V,
  title={VidLoc: 6-DoF Video-Clip Relocalization},
  author={Ronald Clark and Sen Wang and Andrew Markham and Agathoniki Trigoni and Hongkai Wen},
  journal={CoRR},
  year={2017},
  volume={abs/1702.06521}
}
Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases imagesequences, rather only single images, are readily available. To this extent, none of the proposed learning-based approaches exploit the valuable constraint of temporal smoothness, often leading to situations where the per-frame error is larger than the camera motion. In this paper we… CONTINUE READING

Topics

Statistics

05101520172018
Citations per Year

Citation Velocity: 8

Averaging 8 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.