3D Human Pose Estimation in the Wild by Adversarial Learning

@article{Yang20183DHP,
  title={3D Human Pose Estimation in the Wild by Adversarial Learning},
  author={Wei Yang and Wanli Ouyang and X. Wang and J. Ren and Hongsheng Li and Xiaogang Wang},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={5255-5264}
}
  • Wei Yang, Wanli Ouyang, +3 authors Xiaogang Wang
  • Published 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose… CONTINUE READING
    163 Citations

    Figures, Tables, and Topics from this paper

    3D Human Pose Estimation With Generative Adversarial Networks
    3D Human Pose Estimation With Adversarial Learning
    Adversarial learning for viewpoints invariant 3D human pose estimation
    Generalizing Monocular 3D Human Pose Estimation in the Wild
    • Luyang Wang, Yan Chen, +4 authors J. Ren
    • Computer Science
    • 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
    • 2019
    • 12
    • PDF
    Lifting 2d Human Pose to 3d : A Weakly Supervised Approach
    • 2
    • PDF
    View Invariant 3D Human Pose Estimation
    • 2
    • PDF
    Towards Generalization of 3D Human Pose Estimation In The Wild
    • PDF
    Improving Human Pose Estimation With Self-Attention Generative Adversarial Networks
    • 1
    • PDF
    Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
    • 23
    • PDF
    Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
    • 1
    • PDF

    References

    SHOWING 1-10 OF 63 REFERENCES
    Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision
    • 288
    • Highly Influential
    • PDF
    Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation
    • 182
    • Highly Influential
    • PDF
    Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
    • 23
    • Highly Influential
    • PDF
    Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach
    • 293
    • Highly Influential
    • PDF
    A Simple Yet Effective Baseline for 3d Human Pose Estimation
    • 479
    • Highly Influential
    • PDF
    Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
    • 312
    • PDF
    Learning Feature Pyramids for Human Pose Estimation
    • 259
    • PDF
    3D Human Pose Estimation from a Single Image via Distance Matrix Regression
    • F. Moreno-Noguer
    • Computer Science
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 234
    • PDF
    3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network
    • 255
    • PDF
    Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
    • 327
    • PDF