Unsupervised Learning of Depth and Ego-Motion from Video

@article{Zhou2017UnsupervisedLO,
  title={Unsupervised Learning of Depth and Ego-Motion from Video},
  author={Tinghui Zhou and Matthew Brown and Noah Snavely and David G. Lowe},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={6612-6619}
}
  • Tinghui Zhou, Matthew Brown, +1 author David G. Lowe
  • Published in
    IEEE Conference on Computer…
    2017
  • Computer Science
  • We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. [...] Key Method Our method uses single-view depth and multiview pose networks, with a loss based on warping nearby views to the target using the computed depth and pose. The networks are thus coupled by the loss during training, but can be applied independently at test time. Empirical evaluation on the KITTI dataset demonstrates the effectiveness of our approach: 1…Expand Abstract

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

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 620 CITATIONS

    Unsupervised Learning of Camera Pose with Compositional Re-estimation

    VIEW 10 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    End-to-end Network for Monocular Visual Odometry Based on Image Sequence

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Learning of Dense optical Flow, motion and depth, from Sparse Event Cameras

    VIEW 12 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    On-the-fly dense 3D surface reconstruction for geometry-aware augmented reality.

    VIEW 11 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Simultaneous Monocular Visual Odometry and Depth Reconstruction with Scale Recovery*

    • Yong Luo, Guoliang Liu, +3 authors Ze Ji
    • Engineering, Computer Science
    • 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)
    • 2019
    VIEW 9 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Un-VDNet: unsupervised network for visual odometry and depth estimation

    VIEW 6 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach

    VIEW 11 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Self-Supervised Learning of Depth and Camera Motion from 360° Videos

    VIEW 11 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling

    VIEW 14 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 186 Highly Influenced Citations

    • Averaged 188 Citations per year from 2017 through 2019

    • 65% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 59 REFERENCES

    Unsupervised Monocular Depth Estimation with Left-Right Consistency

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Stereo: Learning to Predict New Views from the World's Imagery

    VIEW 8 EXCERPTS

    ORB-SLAM: A Versatile and Accurate Monocular SLAM System

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Are we ready for autonomous driving? The KITTI vision benchmark suite

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    The Cityscapes Dataset for Semantic Urban Scene Understanding

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL