Header logo is ps

Towards Accurate Marker-less Human Shape and Pose Estimation over Time

2017-12-01


Model-based reconstruction of 3D SMPL body shape and pose from multi-view images. 2D joints and silhouettes from multi-view are used in the process. And DCT-based temporal prior is utilized to regularize the recovered 3D joint trajectory.

Author(s): Yinghao Huang and Federica Bogo and Christoph Lassner and Angjoo Kanazawa and Peter V. Gehler and Javier Romero and Ijaz Akhter and Michael J. Black
Department(s): Perceiving Systems
Research Projects(s): Beyond Motion Capture
Publication(s): Towards Accurate Marker-less Human Shape and Pose Estimation over Time
Authors: Yinghao Huang and Federica Bogo and Christoph Lassner and Angjoo Kanazawa and Peter V. Gehler and Javier Romero and Ijaz Akhter and Michael J. Black
Release Date: 2017-12-01
License: Apache License, Version 2.0 (Apache-2.0)
External Link: https://github.com/YinghaoHuang91/MuVS