Back
ExPose
Dataset of expressive 3D humans
It contains ~32k pairs of RGB images and SMPL-X humans (parameters & mehes). It was created by applying SMPLify-X on the LSP, LSP extended and MPII datasets, and carefully curating the results to obtain pseudo ground truth. The dataset was used to train ExPose, a model that predicts expressive 3D humans from an RGB image.
Max Planck Institute for Intelligent Systems, T¨ubingen, Germany
View author website
Task
3D Reconstruction / Photogrammetry
Annotation Types
Semantic Segmentation
32000
Items
3
Classes
32000
Labels
Models using this dataset
Last updated on
January 20, 2022
Licensed under
Research Only
