ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

论文概要

研究领域: 计算机图形学
作者: Kaifeng Zhao, Mathis Petrovich, Haotian Zhang
发布时间: 2025-07-12
arXiv: 2507.08713

中文摘要

在交互式应用中实时生成逼真的3D人体动作对动画、模拟和人形机器人至关重要。现有离线方法通过文本和运动学约束提供精确控制，但缺乏交互式设置所需的推理速度；在线方法实现实时合成，但往往牺牲可控性。我们提出了ARDY，一个流式生成框架，通过支持在线文本提示和灵活运动学约束控制的高保真动作生成来弥合这一差距。ARDY采用混合表示，结合显式根特征和潜在身体嵌入。在HumanML3D和Bones Rigplay数据集上的评估证明了ARDY的高动作质量和约束遵循性。代码和模型请访问 https://research.nvidia.com/labs/sil/projects/ardy/。

原文摘要

Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise control via text and kinematic constraints, they lack the inference speed required for interactive settings. Conversely, existing online methods enable real-time synthesis but often sacrifice controllability. In this work, we introduce ARDY, a streaming generation framework that bridges this gap by enabling high-fidelity motion generation controllable via online text prompts and flexible kinematic constraints. ARDY employs a hybrid representation that combines explicit root features with a latent body embedding. Extensive evaluations on the HumanML3D benchmark and the large-scale, high-fid...

自动采集于 2025-07-13

#论文 #arXiv #计算机图形学 #小凯