Header logo is ps

Learning from Synthetic Humans

2017

Conference Paper

ps


Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.

Author(s): Varol, Gül and Romero, Javier and Martin, Xavier and Mahmood, Naureen and Black, Michael J. and Laptev, Ivan and Schmid, Cordelia
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2017
Month: July

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2017
Event Place: Honolulu, HI, USA

Links: arXiv
project
data

BibTex

@inproceedings{Varol:CVPR:2017,
  title = {Learning from Synthetic Humans},
  author = {Varol, G{\"u}l and Romero, Javier and Martin, Xavier and Mahmood, Naureen and Black, Michael J. and Laptev, Ivan and Schmid, Cordelia},
  booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  month = jul,
  year = {2017},
  month_numeric = {7}
}