Geometric Consistency for Self-Supervised End-to-End Visual Odometry

@article{Iyer2018GeometricCF,
  title={Geometric Consistency for Self-Supervised End-to-End Visual Odometry},
  author={Ganesh Iyer and J. Krishna Murthy and Gunshi Gupta and K. Madhava Krishna and Liam Paull},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2018},
  pages={380-3808}
}
  • Ganesh Iyer, J. Krishna Murthy, +2 authors Liam Paull
  • Published in
    IEEE/CVF Conference on…
    2018
  • Engineering, Computer Science
  • With the success of deep learning based approaches in tackling challenging problems in computer vision, a wide range of deep architectures have recently been proposed for the task of visual odometry (VO) estimation. Most of these proposed solutions rely on supervision, which requires the acquisition of precise ground-truth camera pose information, collected using expensive motion capture systems or high-precision IMU/GPS sensor rigs. In this work, we propose an unsupervised paradigm for deep… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    4
    Twitter Mentions

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 16 CITATIONS

    Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

    • Fei Xue, Xin Wang, +3 authors Hongbin Zha
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019

    Improving Learning-based Ego-motion Estimation with Homomorphism-based Losses and Drift Correction

    VIEW 1 EXCERPT
    CITES METHODS

    Local Pose optimization with an Attention-based Neural Network

    • Yiling Liu, Hesheng Wang, +3 authors Qi-rong Tang
    • Computer Science
    • 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2019
    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES

    ORB-SLAM: A Versatile and Accurate Monocular SLAM System

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    DPC-Net: Deep Pose Correction for Visual Localization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    UnDeepVO: Monocular Visual Odometry Through Unsupervised Deep Learning

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised Learning of Depth and Ego-Motion from Video

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    DeMoN: Depth and Motion Network for Learning Monocular Stereo

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning Visual Odometry with a Convolutional Network

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

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

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL