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 pose recovery through quantitative and qualitative results.
@article{arxiv.1704.03432,
title = {Forecasting Human Dynamics from Static Images},
author = {Yu-Wei Chao and Jimei Yang and Brian Price and Scott Cohen and Jia Deng},
journal= {arXiv preprint arXiv:1704.03432},
year = {2017}
}