Abstraction

Create a special deep learning frame work that have the skeleton structure awareness. This deep learning architecture includes differentiable convolution, pooling and unpooling operators.

Motivation

  1. For motion capture, different company usually used different set of motion capture equipment, different configuration, and different software. “motion retargeting” is introduced
  2. Current convolution network usually used in grid-like data processing rather than articulated network. i.e.: Skeletons of different characters exhibit irregular connectivity.

Contribution

  1. In this paper, we introduce a new motion processing framework consisting of a representation for motion of articulated skeletons
  2. designed for deep learning, and several differentiable operators, including convolution, pooling and unpooling, that operate on this representation.

Problem Formulation

We treat the retargeting problem as a multimodal translation between unpaired domains. All skeletons are homeomorphic.

Image-to-image translation for cross-domain disentanglement