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. Trained CNNs are also provided.
|Author(s):||Varol, Gul and Romero, Javier and Martin, Xavier and Mahmood, Naureen and Black, Michael J. and Laptev, Ivan and Schmid, Cordelia|
|Authors:||Varol, Gul and Romero, Javier and Martin, Xavier and Mahmood, Naureen and Black, Michael J. and Laptev, Ivan and Schmid, Cordelia|
|Copyright:||Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V.|