Corpus ID: 227229064

CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild

@article{Wandt2020CanonPoseSM,
  title={CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild},
  author={B. Wandt and M. Rudolph and P. Zell and Helge Rhodin and B. Rosenhahn},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.14679}
}
Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately. Unfortunately, for many human activities (\eg outdoor sports) such training data does not exist and is hard or even impossible to acquire with traditional motion capture systems. We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data. To this end, we exploit multi-view… Expand
2 Citations

Figures and Tables from this paper

LiftPose3D, a deep learning-based approach for transforming 2D to 3D pose in laboratory animals
  • 3
  • PDF
TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video
  • Highly Influenced
  • PDF

References

SHOWING 1-10 OF 57 REFERENCES
Learning Monocular 3D Human Pose Estimation from Multi-view Images
  • 105
  • PDF
Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild
  • 9
  • Highly Influential
  • PDF
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis
  • 12
  • PDF
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry
  • 93
  • Highly Influential
  • PDF
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision
  • 326
  • PDF
Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
  • 5
  • PDF
Ordinal Depth Supervision for 3D Human Pose Estimation
  • 164
  • PDF
Can 3D Pose be Learned from 2D Projections Alone?
  • 42
  • PDF
Unsupervised 3D Pose Estimation With Geometric Self-Supervision
  • 57
  • PDF
...
1
2
3
4
5
...