EMOSH：用于人体动画的表现性运动与形状解耦
EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
AI总结：
提出EMOSH框架，通过可表现人体模型解耦形状与姿态，结合粗细混合运动注入和空间对齐条件机制，实现高保真、可控的人体视频生成，解决运动-形状纠缠问题。
摘要：
高保真且表现力丰富的可控人体动画对于内容创作和数字虚拟人应用至关重要。然而，现有方法在表现力与解耦之间面临两难。主流的2D姿态驱动方法存在“运动-形状纠缠”，导致驱动主体的身体形状泄露。相反，依赖3D先验（如SMPL）的方法实现了几何解耦，但难以捕捉面部表情和复杂手势，导致动画僵硬。为此，我们提出EMOSH，一种用于高保真可控人体视频生成的新框架。首先，引入可表现人体模型（EHM）作为核心控制表示。通过显式解耦形状和姿态参数，从根本上解决了身体形状泄露问题。同时，设计了一个鲁棒的运动跟踪器，从视频中准确估计EHM参数。其次，我们提出了一种粗细混合运动注入策略，实现了对表情和手势的更精细控制。此外，我们引入了一种空间对齐条件机制，以弥合训练与推理之间的域差距，提高身份一致性。大量实验表明，EMOSH在自驱动和跨驱动场景中均优于先前方法，在保持形状解耦的同时生成具有生动表情的高保真视频。
英文摘要：
High-fidelity and expressive controllable human animation is essential for content creation and digital avatar applications. However, existing methods face a dilemma between expressiveness and disentanglement. Mainstream 2D pose-conditioned approaches suffer from "motion-shape entanglement", leading to the leakage of the driving subject's body shape. Conversely, methods relying on 3D priors (e.g., SMPL) achieve geometric disentanglement but struggle to capture facial expressions and complex gestures, resulting in rigid animations. To this end, we propose EMOSH, a novel framework for high-fidelity controllable human video generation. First, an Expressive Human Model (EHM) is introduced as the core control representation. By explicitly disentangling shape and pose parameters, we fundamentally resolve the body shape leakage issue. Alongside this, a robust motion tracker is designed to accurately estimate EHM parameters from video. Second, we propose a Coarse-to-Fine Hybrid Motion Injection strategy, enabling more fine-grained control over expressions and gestures. Furthermore, we introduce a Spatially-Aligned Conditioning mechanism to bridge the domain gap between training and inference, improving identity consistency. Extensive experiments demonstrate that EMOSH outperforms previous methods in both self-driven and cross-driven scenarios, producing high-fidelity videos with vivid expressions while maintaining shape disentanglement.
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。
