On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation

@article{Cavallari2017OntheFlyAO,
  title={On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation},
  author={Tommaso Cavallari and Stuart Golodetz and Nicholas A. Lord and Julien P. C. Valentin and Luigi di Stefano and Philip H. S. Torr},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={218-227}
}
  • Tommaso Cavallari, Stuart Golodetz, +3 authors Philip H. S. Torr
  • Published 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 55 CITATIONS

    Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS

    Backtracking regression forests for accurate camera relocalization

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization

    VIEW 1 EXCERPT
    CITES BACKGROUND

    [POSTER] Decision Forest For Efficient and Robust Camera Relocalization

    Decoupling Features and Coordinates for Few-shot RGB Relocalization

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    Learning Less is More - 6D Camera Localization via 3D Surface Regression

    VIEW 2 EXCERPTS
    CITES RESULTS & BACKGROUND

    SIR-Net: Scene-Independent End-to-End Trainable Visual Relocalizer

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 3 Highly Influenced Citations

    • Averaged 16 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES

    Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Exploiting uncertainty in regression forests for accurate camera relocalization

    VIEW 12 EXCERPTS

    Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Multi-output Learning for Camera Relocalization

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

    VIEW 1 EXCERPT

    Large-scale and drift-free surface reconstruction using online subvolume registration

    VIEW 1 EXCERPT

    Fast relocalisation and loop closing in keyframe-based SLAM

    VIEW 3 EXCERPTS

    Real-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Efficient & Effective Prioritized Matching for Large-Scale Image-Based Localization

    VIEW 1 EXCERPT