Contact-Aware Retargeting of Skinned Motion

TL;DR

This paper presents a novel motion retargeting method that maintains self-contacts and prevents interpenetration, resulting in more realistic and higher-quality human motion transfer across different skeletons and geometries.

Contribution

It introduces a geometry-conditioned recurrent network with encoder-space optimization to preserve contact attributes and reduce interpenetration during motion retargeting.

Findings

Quantitative results outperform previous methods.

User study favors the proposed retargeting quality.

Generalizes well to motion estimated from videos.

Abstract

This paper introduces a motion retargeting method that preserves self-contacts and prevents interpenetration. Self-contacts, such as when hands touch each other or the torso or the head, are important attributes of human body language and dynamics, yet existing methods do not model or preserve these contacts. Likewise, interpenetration, such as a hand passing into the torso, are a typical artifact of motion estimation methods. The input to our method is a human motion sequence and a target skeleton and character geometry. The method identifies self-contacts and ground contacts in the input motion, and optimizes the motion to apply to the output skeleton, while preserving these contacts and reducing interpenetration. We introduce a novel geometry-conditioned recurrent network with an encoder-space optimization strategy that achieves efficient retargeting while satisfying contact constraints. In experiments, our results quantitatively outperform previous methods and we conduct a user study where our retargeted motions are rated as higher-quality than those produced by recent works. We also show our method generalizes to motion estimated from human videos where we improve over previous works that produce noticeable interpenetration.