DreamActor-M2：基于时空上下文学习的通用角色图像动画技术

DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning

January 29, 2026

作者: Mingshuang Luo, Shuang Liang, Zhengkun Rong, Yuxuan Luo, Tianshu Hu, Ruibing Hou, Hong Chang, Yong Li, Yuan Zhang, Mingyuan Gao

cs.AI

摘要

角色图像动画旨在通过将驱动序列中的运动迁移至静态参考图像，合成高保真视频。尽管近期取得进展，现有方法仍面临两个核心挑战：（1）次优的运动注入策略导致身份保持与运动一致性之间出现"跷跷板"效应；（2）过度依赖显式姿态先验（如骨骼结构），难以捕捉复杂动态，且阻碍对任意非人形角色的泛化能力。为解决这些问题，我们提出DreamActor-M2——一个将运动条件重构为情境学习问题的通用动画框架。该方法采用两阶段范式：首先通过将外观特征与运动线索融合至统一潜空间，弥合输入模态差异，使模型能基于基础模型的生成先验协同推理空间身份与时间动态；其次引入自举数据合成流程，构建伪跨身份训练样本对，实现从依赖姿态控制到端到端RGB驱动动画的无缝过渡。该策略显著提升了跨角色类型与运动场景的泛化能力。为促进全面评估，我们进一步提出涵盖多维度角色类型与运动场景的通用基准AW Bench。大量实验表明，DreamActor-M2实现了业界领先的性能，在视觉保真度与跨域泛化性方面均表现优异。项目页面：https://grisoon.github.io/DreamActor-M2/

English

Character image animation aims to synthesize high-fidelity videos by transferring motion from a driving sequence to a static reference image. Despite recent advancements, existing methods suffer from two fundamental challenges: (1) suboptimal motion injection strategies that lead to a trade-off between identity preservation and motion consistency, manifesting as a "see-saw", and (2) an over-reliance on explicit pose priors (e.g., skeletons), which inadequately capture intricate dynamics and hinder generalization to arbitrary, non-humanoid characters. To address these challenges, we present DreamActor-M2, a universal animation framework that reimagines motion conditioning as an in-context learning problem. Our approach follows a two-stage paradigm. First, we bridge the input modality gap by fusing reference appearance and motion cues into a unified latent space, enabling the model to jointly reason about spatial identity and temporal dynamics by leveraging the generative prior of foundational models. Second, we introduce a self-bootstrapped data synthesis pipeline that curates pseudo cross-identity training pairs, facilitating a seamless transition from pose-dependent control to direct, end-to-end RGB-driven animation. This strategy significantly enhances generalization across diverse characters and motion scenarios. To facilitate comprehensive evaluation, we further introduce AW Bench, a versatile benchmark encompassing a wide spectrum of characters types and motion scenarios. Extensive experiments demonstrate that DreamActor-M2 achieves state-of-the-art performance, delivering superior visual fidelity and robust cross-domain generalization. Project Page: https://grisoon.github.io/DreamActor-M2/