Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance

Key points

• To close this gap, we focus on the Exaggeration principle of animation and investigate how it can be incorporated into modern motion generative pipelines to produce more expressive character motions.1
• To this end, we introduce a framework that operates at two stages of existing motion generative pipelines.1
• The second stage operates at inference time, where we: (i) introduce a mathematical formulation of exaggeration based on dynamic movement primitives (DMPs); and (ii) leverage this formulation as an exaggeration guidance signal to guide existing diffusion and flow-matching text-to-motion generation models toward exaggerated motion without additional training.1
• Through qualitative and quantitative evaluations against three strong motion generation models, we show that our methods generate more exaggerated and expressive motions while preserving neutral reference motion intent and physical plausibility.1

Sources (1)

• [1]Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 05:00 PM

  Recent motion generative models have demonstrated strong capabilities in synthesizing physically plausible character motion, but often overlook established animation principles used by professional animators to ground and design their animation work.

  To close this gap, we focus on the Exaggeration principle of animation and investigate how it can be incorporated into modern motion generative pipelines to produce more expressive character motions.

Extractive summary: sentences quoted from the sources.