PhyMotion: 结构化3D运动奖励用于物理基础的人体视频生成
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
AI总结：
本文提出PhyMotion，一种结构化的3D运动奖励机制，通过物理模拟器评估人体运动的物理可行性，提升视频生成中人体动作的真实感。
摘要：
生成逼真的人体运动是视频生成中的核心但尚未解决的挑战。尽管基于强化学习（RL）的后训练方法在一般视频质量上取得了进展，但将其扩展到人体运动仍受制于无法可靠评分运动真实性的奖励信号。现有视频奖励主要依赖2D感知信号，未显式建模人体运动的3D身体状态、接触和动力学。为了解决这一问题，我们提出了PhyMotion，一种结构化、细粒度的运动奖励，将恢复的3D人体轨迹嵌入物理模拟器中，并在多个物理可行性维度上评估运动质量。具体来说，我们从生成的视频中恢复SMPL身体网格，将其重新定位到MuJoCo物理模拟器中的仿人机器人，并在三个轴上评估所得运动：运动学合理性、接触和平衡一致性以及动态可行性。每个组件提供连续且可解释的信号，与运动质量的特定方面相关联，使奖励能够捕捉哪些运动方面是物理上正确的或违反的。实验表明，PhyMotion在与人类判断的相关性方面优于现有奖励公式。这些收益延伸到基于RL的后训练中，其中优化PhyMotion导致比优化现有奖励更大的改进，提高了自动指标和盲人人类评估下的运动真实感（+68 Elo gain）。消融实验表明，三个轴提供了互补的监督信号，而奖励在仅小幅训练开销下保持了整体视频生成质量。
英文摘要：
Generating realistic human motion is a central yet unsolved challenge in video generation. While reinforcement learning (RL)-based post-training has driven recent gains in general video quality, extending it to human motion remains bottlenecked by a reward signal that cannot reliably score motion realism. Existing video rewards primarily rely on 2D perceptual signals, without explicitly modeling the 3D body state, contact, and dynamics underlying articulated human motion, and often assign high scores to videos with floating bodies or physically implausible movements. To address this, we propose PhyMotion, a structured, fine-grained motion reward that grounds recovered 3D human trajectories in a physics simulator and evaluates motion quality along multiple dimensions of physical feasibility. Concretely, we recover SMPL body meshes from generated videos, retarget them onto a humanoid in the MuJoCo physics simulator, and evaluate the resulting motion along three axes: kinematic plausibility, contact and balance consistency, and dynamic feasibility. Each component provides a continuous and interpretable signal tied to a specific aspect of motion quality, allowing the reward to capture which aspects of motion are physically correct or violated. Experiments show that PhyMotion achieves stronger correlation with human judgments than existing reward formulations. These gains carry over to RL-based post-training, where optimizing PhyMotion leads to larger and more consistent improvements than optimizing existing rewards, improving motion realism across both autoregressive and bidirectional video generators under both automatic metrics and blind human evaluation (+68 Elo gain). Ablations show that the three axes provide complementary supervision signals, while the reward preserves overall video generation quality with only modest training overhead.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
