Morph：一個針對人體動作生成的無運動物理優化框架

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

November 22, 2024

作者: Zhuo Li, Mingshuang Luo, Ruibing Hou, Xin Zhao, Hao Liu, Hong Chang, Zimo Liu, Chen Li

cs.AI

摘要

人類動作生成在數位人類和人形機器人控制等應用中扮演著重要角色。然而，大多數現有方法忽略物理約束，導致生成的動作常常不合物理規律，出現明顯的問題，如漂浮和腳部滑動。本文提出了一個名為Morph的無動作物理優化框架，包括一個動作生成器和一個動作物理細化模組，用於提高物理合理性，而無需依賴昂貴的現實世界動作數據。具體而言，動作生成器負責提供大規模的合成動作數據，而動作物理細化模組利用這些合成數據在物理模擬器中訓練動作模仿者，強制實施物理約束，將嘈雜的動作投影到一個符合物理規律的空間。這些經過物理細化的動作進而用於微調動作生成器，進一步提升其能力。在文本轉動作和音樂轉舞蹈生成任務上的實驗表明，我們的框架實現了最先進的動作生成質量，同時極大地提高了物理合理性。

English

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 Morph, a Motion-free physics 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.