DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies

TL;DR

DancingBox is a lightweight, vision-based system that enables novices to create realistic character animations using everyday objects as proxies, leveraging generative models and large-scale motion priors.

Contribution

It introduces a novel proxy-based motion capture approach that simplifies character animation for beginners by combining coarse proxy tracking with learned motion priors.

Findings

Enables intuitive animation with diverse proxies

Reduces barrier for novice animators

Synthesizes training data from existing motion capture sequences

Abstract

Creating compelling 3D character animations typically requires either expert use of professional software or expensive motion capture systems operated by skilled actors. We present DancingBox, a lightweight, vision-based system that makes motion capture accessible to novices by reimagining the process as digital puppetry. Instead of tracking precise human motions, DancingBox captures the approximate movements of everyday objects manipulated by users with a single webcam. These coarse proxy motions are then refined into realistic character animations by conditioning a generative motion model on bounding-box representations, enriched with human motion priors learned from large-scale datasets. To overcome the lack of paired proxy-animation data, we synthesize training pairs by converting existing motion capture sequences into proxy representations. A user study demonstrates that DancingBox enables intuitive and creative character animation using diverse proxies, from plush toys to bananas, lowering the barrier to entry for novice animators.