Computer Graphics
TU Braunschweig

Optical Flow-based 3D Human Motion Estimation from Monocular Video


Optical Flow-based 3D Human Motion Estimation from Monocular Video

We present a generative method to estimate 3D human motion and body shape from monocular video. Under the assumption that starting from an initial pose optical flow constrains subsequent human motion, we exploit flow to find temporally coherent human poses of a motion sequence. We estimate human motion by minimizing the difference between computed flow fields and the output of an artificial flow renderer. A single initialization step is required to estimate motion over multiple frames. Several regularization functions enhance robustness over time. Our test scenarios demonstrate that optical flow effectively regularizes the under-constrained problem of human shape and motion estimation from monocular video.


Author(s):Thiemo Alldieck, Marc Kassubeck, Marcus Magnor
Year:2017
Month:March
Type:Misc
Howpublished:arXiv preprint
Note:arXiv:1703.00177
Project(s): Comprehensive Human Performance Capture from Monocular Video Footage 


@misc{alldieck2017optical,
  title = {Optical Flow-based 3D Human Motion Estimation from Monocular Video},
  author = {Alldieck, Thiemo and Kassubeck, Marc and Magnor, Marcus},
  howpublished = {arXiv preprint},
  note = {arXiv:1703.00177},
  month = {Mar},
  year = {2017}
}

Authors