超越形态:从抽象运动表示引导跨类别运动迁移
原标题:Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
AI 摘要
Hugging Face 每日论文发布了一篇关于视频运动迁移的新研究,提出了一种名为 Motion Beyond Morphology (MBM) 的框架,旨在解决参考视频与目标对象在形态、关节或变形机制上差异较大时的运动迁移问题。该框架通过两阶段学习,利用多粒度抽象运动表示引导跨类别视频对,并在推理时直接基于参考视频生成,无需显式运动提取。实验表明,在相同、相近和远距离类别差距下,该方法在运动保真度和目标保留方面达到了最先进水平,并计划发布 OpenVMT-Dataset 和 OpenVMT-Bench 数据集。
正文节选
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations Abstract Video motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes ill-defined when reference and target objects differ substantially in morphology, articulation, or deformation mechanisms. We introduce Motion Beyond Morphology, a perspective that seeks to transfer motion