MultiAnimate：可扩展的姿态引导图像动画
MultiAnimate: Pose-Guided Image Animation Made Extensible
基于 DiT 视频生成框架，用掩码驱动的 Identifier Assigner/Adapter 注入逐人位置线索与人物间空间关系，可复用于任何需要多实例身份解耦的可控视频生成任务。
原文依据 an extensible multi-character image animation framework built upon modern Diffusion Transformers (DiTs) for video generation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论姿态引导的人体图像动画旨在合成由一系列姿态驱动的参考角色的逼真视频。尽管基于扩散的方法已取得显著成功，但现有方法大多局限于单角色动画。我们观察到，将这些方法朴素地扩展到多角色场景往往会导致身份混淆以及角色之间不合理的遮挡。为应对这些挑战，本文提出一个可扩展的多角色图像动画框架，构建于现代视频生成扩散 Transformer（DiT）之上。该框架的核心引入了两个新颖组件——标识分配器（Identifier Assigner）与标识适配器（Identifier Adapter）——二者协同捕获逐人的位置线索与人物间的空间关系。这种掩码驱动的方案连同可扩展的训练策略，不仅提升了灵活性，还使其能够泛化到比训练时所见角色数量更多的场景。值得注意的是，我们的模型仅在双角色数据集上训练，却能泛化到多角色动画，同时保持与单角色情形的兼容性。大量实验表明，我们的方法在多角色图像动画上达到最优性能，超越了现有的基于扩散的基线方法。代码将公开。
英文原文摘要 1354 字符
Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to single-character animation. We observe that naively extending these methods to multi-character scenarios often leads to identity confusion and implausible occlusions between characters. To address these challenges, in this paper, we propose an extensible multi-character image animation framework built upon modern Diffusion Transformers (DiTs) for video generation. At its core, our framework introduces two novel components--Identifier Assigner and Identifier Adapter--which collaboratively capture per-person positional cues and inter-person spatial relationships. This mask-driven scheme, along with a scalable training strategy, not only enhances flexibility but also enables generalization to scenarios with more characters than those seen during training. Remarkably, trained on only a two-character dataset, our model generalizes to multi-character animation while maintaining compatibility with single-character cases. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in multi-character image animation, surpassing existing diffusion-based baselines. Codes will be released.