Human motion generation plays a vital role in applications such as digital humans and humanoid robot control. However, most existing approaches disregard physics constraints, leading to the frequent production of physically implausible motions with pronounced artifacts such as floating and foot sliding. In this paper, we propose \textbf{Morph}, a \textbf{Mo}tion-f\textbf{r}ee \textbf{ph}ysics optimization framework, comprising a Motion Generator and a Motion Physics Refinement module, for enhancing physical plausibility without relying on costly real-world motion data. Specifically, the Motion Generator is responsible for providing large-scale synthetic motion data, while the Motion Physics Refinement Module utilizes these synthetic data to train a motion imitator within a physics simulator, enforcing physical constraints to project the noisy motions into a physically-plausible space. These physically refined motions, in turn, are used to fine-tune the Motion Generator, further enhancing its capability. Experiments on both text-to-motion and music-to-dance generation tasks demonstrate that our framework achieves state-of-the-art motion generation quality while improving physical plausibility drastically.

翻译：人体运动生成在数字人和仿人机器人控制等应用中起着至关重要的作用。然而，现有的大多数方法忽略了物理约束，导致频繁产生物理上不合理的运动，并伴有明显的伪影，如漂浮和脚部滑动。本文提出 \textbf{Morph}，一个 \textbf{免运动物理优化框架}，包含一个运动生成器和一个运动物理精炼模块，旨在不依赖昂贵的真实世界运动数据的情况下提升物理合理性。具体而言，运动生成器负责提供大规模合成运动数据，而运动物理精炼模块则利用这些合成数据，在物理模拟器中训练一个运动模仿器，通过施加物理约束将含噪声的运动投影到物理合理的空间中。这些经过物理精炼的运动反过来被用于微调运动生成器，从而进一步提升其能力。在文本到运动和音乐到舞蹈生成任务上的实验表明，我们的框架在显著提升物理合理性的同时，实现了最先进的运动生成质量。