实时生成稳定长序列角色动作，支持任意关节精细控制
Controllable Long-term Motion Generation with Extended Joint Targets
- 基于Transformer的条件变分自编码器实现高效交互控制
- 引入参考引导反馈机制，避免长时间动作误差累积
- 支持实时风格迁移，适合高要求互动应用
在计算机动画中，实现实时、稳定的可控角色动作生成是一项关键挑战。现有方法往往难以提供细粒度控制或在长序列中出现动作退化，限制了其在交互式应用中的使用。我们提出COMET，一种可实时运行的自回归框架，实现多样化角色控制与鲁棒的长时序合成。基于Transformer的高效条件变分自编码器允许对任意用户指定关节进行精确、交互式控制，适用于目标达成和中间补全等任务。为确保长期时间稳定性，我们引入一种新颖的参考引导反馈机制，有效防止误差累积，该机制还可作为即插即用的风格化模块，支持实时风格迁移。大量实验表明，COMET在实时速度下能稳健生成高质量动作，在复杂运动控制任务中显著优于当前最优方法，证实其适用于高要求交互应用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。