Forecasting Human Dynamics from Static Images

Yu-Wei Chao, Jimei Yang, Brian Price, Scott Cohen, Jia Deng

CVPR 2017

doi:10.1109/CVPR.2017.388 /cvpr/2017/chao2017cvpr-forecasting/

Abstract

This paper presents the first study on forecasting human dynamics from static images. The problem is to input a single RGB image and generate a sequence of upcoming human body poses in 3D. To address the problem, we propose the 3D Pose Forecasting Network (3D-PFNet). Our 3D-PFNet integrates recent advances on single-image human pose estimation and sequence prediction, and converts the 2D predictions into 3D space. We train our 3D-PFNet using a three-step training strategy to leverage a diverse source of training data, including image and video based human pose datasets and 3D motion capture (MoCap) data. We demonstrate competitive performance of our 3D-PFNet on 2D pose forecasting and 3D structure recovery through quantitative and qualitative results.

PDF CVPR Semantic Scholar

Cite

Text

Chao et al. "Forecasting Human Dynamics from Static Images." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.388

Markdown

[Chao et al. "Forecasting Human Dynamics from Static Images." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/chao2017cvpr-forecasting/) doi:10.1109/CVPR.2017.388

BibTeX

@inproceedings{chao2017cvpr-forecasting,
  title     = {{Forecasting Human Dynamics from Static Images}},
  author    = {Chao, Yu-Wei and Yang, Jimei and Price, Brian and Cohen, Scott and Deng, Jia},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.388},
  url       = {https://mlanthology.org/cvpr/2017/chao2017cvpr-forecasting/}
}