SURREAL Dataset

Synthetic hUmans foR REAL tasks

First large-scale person dataset to generate depth, body parts, optical flow, 2D/3D pose, surface normals ground truth for RGB video input. The dataset contains 6M frames of synthetic humans. The images are photo-realistic renderings of people under large variations in shape, texture, view-point and pose. To ensure realism, the synthetic bodies are created using the SMPL body model, whose parameters are fit by the MoSh method given raw 3D MoCap marker data.

*** News *** The release now includes the optical flow data.

BibTeX

When using SURREAL please reference:
@INPROCEEDINGS{varol17_surreal,
  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 = {CVPR},
  year      = {2017}
}

More information