Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published September 1, 2020 | Version Accepted pre-print
Journal article Open

MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency

  • 1. Shandong University and AICFVE, Beijing Film Academy
  • 2. AICFVE, Beijing Film Academy and Tel-Aviv University
  • 3. University of Cyprus and RISE Research Centre
  • 4. Edinburgh University
  • 5. Shandong University, The Hebrew University of Jerusalem, and AICFVE, Beijing Film Academy
  • 6. Tel-Aviv University and AICFVE, Beijing Film Academy
  • 7. CFCS, Peking University and AICFVE, Beijing Film Academy

Description

We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation. At the crux of our approach lies a deep neural network with embedded kinematic priors, which decomposes sequences of 2D joint positions into two separate attributes: a single, symmetric, skeleton, encoded by bone lengths, and a sequence of 3D joint rotations associated with global root positions and foot contact labels. These attributes are fed into an integrated forward kinematics (FK) layer that outputs 3D positions, which are compared to a ground truth. In addition, an adversarial loss is applied to the velocities of the recovered rotations, to ensure that they lie on the manifold of natural joint rotations.
The key advantage of our approach is that it learns to infer natural joint rotations directly from the training data, rather than assuming an underlying model, or inferring them from joint positions using a data-agnostic IK solver. We show that enforcing a single consistent skeleton along with temporally coherent joint rotations constrains the solution space, leading to a more robust handling of self-occlusions and depth ambiguities.

Notes

This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.

Files

2006.12075.pdf

Files (4.2 MB)

Name Size Download all
md5:13c465e299170e9f7fd9e9e33116ecd9
4.2 MB Preview Download

Additional details

Funding

RISE – Research Center on Interactive Media, Smart System and Emerging Technologies 739578
European Commission