Header logo is ps

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image


Conference Paper


To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8x over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

Author(s): Georgios Pavlakos and Vasileios Choutas and Nima Ghorbani and Timo Bolkart and Ahmed A. A. Osman and Dimitrios Tzionas and Michael J. Black
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Pages: 10975--10985
Year: 2019
Month: June

Department(s): Perceiving Systems
Research Project(s): 3D Body Shape and Pose from Images
Expressive Body Models
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: https://doi.org/10.1109/CVPR.2019.01123
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019
Event Place: Long Beach, USA

URL: http://smpl-x.is.tue.mpg.de

Links: video
Attachments: pdf


  title = {Expressive Body Capture: 3D Hands, Face, and Body from a Single Image},
  author = {Pavlakos, Georgios and Choutas, Vasileios and Ghorbani, Nima and Bolkart, Timo and Osman, Ahmed A. A. and Tzionas, Dimitrios and Black, Michael J.},
  booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  pages = {10975--10985},
  month = jun,
  year = {2019},
  url = {http://smpl-x.is.tue.mpg.de},
  month_numeric = {6}