PoseAnything：具有部件感知时序一致性的通用姿态引导视频生成
PoseAnything: General Pose-guided Video Generation with Part-aware Temporal Coherence
把任意骨架（含非人类角色）作为运动条件注入视频扩散模型，并用部件级跨帧交叉注意力维持细粒度一致性；其解耦主体/相机运动的 CFG 正负锚点注入方式可直接迁移到其他可控视频生成任务中实现独立相机控制。
原文依据 computes cross-attention between corresponding parts across frames to achieve fine-grained part-level consistency
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视频生成是指通过一系列姿态来控制生成视频中主体的运动。它能够实现对主体运动的精确控制，在动画领域具有重要应用。然而，当前的姿态引导视频生成方法仅能接受人体姿态作为输入，因而对其他主体姿态的泛化能力较差。为解决这一问题，我们提出 PoseAnything，一个通用的姿态引导视频生成框架，能够处理人类与非人类角色，并支持任意骨架输入。为增强运动过程中的一致性保持，我们引入部件感知时序一致性模块，该模块将主体划分为不同部件、建立部件对应关系，并计算跨帧对应部件之间的交叉注意力，从而实现细粒度的部件级一致性。此外，我们提出主体与相机运动解耦 CFG，这是一种新颖的引导策略，首次在姿态引导视频生成中实现独立的相机运动控制，其做法是将主体运动与相机运动的控制信息分别注入 CFG 的正锚点与负锚点。进一步地，我们提出 XPose，一个包含 50,000 个非人类姿态-视频对的高质量公开数据集，以及配套的自动化标注与筛选流程。大量实验表明，PoseAnything 在有效性与泛化性上均显著优于最优方法。
英文原文摘要 1493 字符
Pose-guided video generation refers to controlling the motion of subjects in generated video through a sequence of poses. It enables precise control over subject motion and has important applications in animation. However, current pose-guided video generation methods are limited to accepting only human poses as input, thus generalizing poorly to pose of other subjects. To address this issue, we propose PoseAnything, a general pose-guided video generation framework capable of handling both human and non-human characters, supporting arbitrary skeletal inputs. To enhance consistency preservation during motion, we introduce Part-aware Temporal Coherence Module, which divides the subject into different parts, establishes part correspondences, and computes cross-attention between corresponding parts across frames to achieve fine-grained part-level consistency. Additionally, we propose Subject and Camera Motion Decoupled CFG, a novel guidance strategy that, for the first time, enables independent camera movement control in pose-guided video generation, by separately injecting subject and camera motion control information into the positive and negative anchors of CFG. Furthermore, we present XPose, a high-quality public dataset containing 50,000 non-human pose-video pairs, along with an automated pipeline for annotation and filtering. Extensive experiments demonstrate that PoseAnything significantly outperforms state-of-the-art methods in both effectiveness and generalization.