First dataset for computer vision research 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. No 3D meshes nor raw files of the models are provided. License
We can NOT share the 3D meshes nor raw files of the models for copyright reasons. The animations used are from the CMU MoCap database.
When using 3DPeople Dataset please reference: