Learning 3D Human Dynamics From Video

@article{Kanazawa2019Learning3H,
  title={Learning 3D Human Dynamics From Video},
  author={Angjoo Kanazawa and Jason Y. Zhang and Panna Felsen and Jitendra Malik},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={5607-5616}
}
  • Angjoo Kanazawa, Jason Y. Zhang, +1 author Jitendra Malik
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of humans in motion. We present a framework that can similarly learn a representation of 3D dynamics of humans from video via a simple but effective temporal encoding of image features. At test time, from video, the learned temporal representation give rise to… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 57 CITATIONS, ESTIMATED 58% COVERAGE

    Predicting 3D Human Dynamics From Video

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS

    Exploiting Temporal Context for 3D Human Pose Estimation in the Wild

    VIEW 1 EXCERPT
    CITES METHODS

    VIBE: Video Inference for Human Body Pose and Shape Estimation

    VIEW 17 EXCERPTS
    CITES METHODS, BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    Learning to Predict Human Behavior from Video

    VIEW 5 EXCERPTS
    CITES BACKGROUND

    Self-Supervised Human Depth Estimation from Monocular Videos

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Sim2real transfer learning for 3D pose estimation: motion to the rescue

    VIEW 5 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 15 Highly Influenced Citations

    • Averaged 19 Citations per year from 2018 through 2020

    • 20% Increase in citations per year in 2020 over 2019

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 74 REFERENCES

    Forecasting Human Dynamics from Static Images

    VIEW 2 EXCERPTS

    Im2Flow: Motion Hallucination from Static Images for Action Recognition

    VIEW 1 EXCERPT

    3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training

    VIEW 1 EXCERPT

    3D Reconstruction of Human Motion from Monocular Image Sequences

    VIEW 1 EXCERPT

    Unite the People: Closing the Loop Between 3D and 2D Human Representations

    VIEW 1 EXCERPT

    Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video

    VIEW 1 EXCERPT