Towards CNN Map Representation and Compression for Camera Relocalisation

@article{Contreras2018TowardsCM,
  title={Towards CNN Map Representation and Compression for Camera Relocalisation},
  author={Luis Contreras and Walterio W. Mayol-Cuevas},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2018},
  pages={405-4057}
}
  • Luis Contreras, Walterio W. Mayol-Cuevas
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 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… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES
    VidLoc: 6-DoF Video-Clip Relocalization
    22
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    37654
    Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
    645
    Return of the Devil in the Details: Delving Deep into Convolutional Nets
    2575
    PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
    814
    Going deeper with convolutions
    19171
    Learning Image Matching by Simply Watching Video
    92
    Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
    585
    Real-time RGB-D camera relocalization
    68
    6D Relocalisation for RGBD Cameras Using Synthetic View Regression
    37