by Albert PumarolaResearch Only
by Albert PumarolaLicense : Research Only
First dataset of dressed humans with specific geometry representation for the clothes. It contains ~2 Million images with 40 male/40 female performing 70 actions. Every subject-action sequence is captured from 4 camera views and annotated with: RGB, 3D skeleton, body part and cloth segmentation masks, depth map, optical flow, and camera parameters.
SensorRGB-D, Segmentation Masks