Header logo is ps

Resolving {3D} Human Pose Ambiguities with {3D} Scene Constraints


Conference Paper


To understand and analyze human behavior, we need to capture humans moving in, and interacting with, the world. Most existing methods perform 3D human pose estimation without explicitly considering the scene. We observe however that the world constrains the body and vice-versa. To motivate this, we show that current 3D human pose estimation methods produce results that are not consistent with the 3D scene. Our key contribution is to exploit static 3D scene structure to better estimate human pose from monocular images. The method enforces Proximal Relationships with Object eXclusion and is called PROX. To test this, we collect a new dataset composed of 12 different 3D scenes and RGB sequences of 20 subjects moving in and interacting with the scenes. We represent human pose using the 3D human body model SMPL-X and extend SMPLify-X to estimate body pose using scene constraints. We make use of the 3D scene information by formulating two main constraints. The interpenetration constraint penalizes intersection between the body model and the surrounding 3D scene. The contact constraint encourages specific parts of the body to be in contact with scene surfaces if they are close enough in distance and orientation. For quantitative evaluation we capture a separate dataset with 180 RGB frames in which the ground-truth body pose is estimated using a motion-capture system. We show quantitatively that introducing scene constraints significantly reduces 3D joint error and vertex error. Our code and data are available for research at https://prox.is.tue.mpg.de.

Author(s): Mohamed Hassan and Vasileios Choutas and Dimitrios Tzionas and Michael J. Black
Book Title: Proceedings International Conference on Computer Vision
Pages: 2282--2292
Year: 2019
Month: October
Day: 27
Publisher: IEEE

Department(s): Perceiving Systems
Research Project(s): Bodies from RGB-D
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: https://doi.org/10.1109/ICCV.2019.00237
Event Name: International Conference on Computer Vision
Event Place: Seoul, South Korea

State: Published
URL: https://prox.is.tue.mpg.de
Attachments: pdf


  title = {Resolving {3D} Human Pose Ambiguities with {3D} Scene Constraints},
  author = {Hassan, Mohamed and Choutas, Vasileios and Tzionas, Dimitrios and Black, Michael J.},
  booktitle = {Proceedings International Conference on Computer Vision},
  pages = {2282--2292},
  publisher = {IEEE},
  month = oct,
  year = {2019},
  url = {https://prox.is.tue.mpg.de},
  month_numeric = {10}