Controllable Long-term Motion Generation with Extended Joint Targets

TL;DR

COMET is a real-time autoregressive framework using Transformer-based conditional VAE for controllable, stable long-term character motion generation with style transfer capabilities.

Contribution

It introduces COMET, a novel real-time motion generation method with a reference-guided feedback mechanism for long-term stability and style transfer.

Findings

Outperforms state-of-the-art in complex motion control tasks

Generates high-quality motion at real-time speeds

Ensures long-term temporal stability

Abstract

Generating stable and controllable character motion in real-time is a key challenge in computer animation. Existing methods often fail to provide fine-grained control or suffer from motion degradation over long sequences, limiting their use in interactive applications. We propose COMET, an autoregressive framework that runs in real time, enabling versatile character control and robust long-horizon synthesis. Our efficient Transformer-based conditional VAE allows for precise, interactive control over arbitrary user-specified joints for tasks like goal-reaching and in-betweening from a single model. To ensure long-term temporal stability, we introduce a novel reference-guided feedback mechanism that prevents error accumulation. This mechanism also serves as a plug-and-play stylization module, enabling real-time style transfer. Extensive evaluations demonstrate that COMET robustly generates high-quality motion at real-time speeds, significantly outperforming state-of-the-art approaches in complex motion control tasks and confirming its readiness for demanding interactive applications.