发表机构
KAIST, Visual Media Lab（韩国科学技术院视觉媒体实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ReCHOIR提出接触引导的重定向方法，利用部分感知运动嵌入和接触条件，在多样角色间迁移人-物交互运动，保持语义和交互一致性。
AI 中文摘要
我们提出了ReCHOIR，一种新颖的接触引导的运动重定向方法，用于在多样的人形角色之间迁移人-物交互（HOI）运动。与先前主要关注仅迁移人体运动的运动重定向方法不同，我们的目标不仅是保留原始身体运动的语义，还要保持角色与被操作物体之间一致的交互，同时联合生成对齐的目标人体和物体运动。给定源HOI运动、物体几何形状以及从源交互中提取的接触线索，ReCHOIR将HOI序列重定向到具有不同骨骼配置的目标角色，同时保持运动语义和接触一致的交互模式。我们的方法构建于部分感知运动嵌入（PAME）自编码器之上，该自编码器将全身运动编码到共享的基于身体部分的潜在空间中。这种表示能够在异构骨骼之间实现泛化，同时保留局部运动语义，有利于HOI重定向中的部分感知适应。在此表示之上，我们引入了接触引导的重定向模块和用于HOI重定向的物体运动解码器。接触引导的重定向模块将源物体交互视为细化目标角色运动的条件：物体和接触相关的信号被编码为与身体部分对齐的潜在表示，并通过残差控制分支注入到解码中，从而在不丢弃底层运动先验的情况下，在交互相关的身体区域实现更强的适应。同时，物体运动解码器预测与细化后的目标角色运动对齐的目标物体运动，确保物体轨迹与目标角色实现交互的方式保持一致。
英文摘要
We present ReCHOIR, a novel contact-guided motion retargeting method for transferring human object interaction (HOI) motions across diverse humanoid characters. Unlike prior motion retargeting methods that primarily focus on transferring human motion alone, our goal is to preserve not only the semantics of the original body movement but also consistent interaction between the character and the manipulated object, while jointly producing aligned target human and object motions. Given source HOI motion, object geometry, and contact cues extracted from the source interaction, ReCHOIR retargets an HOI sequence to target characters with different skeletal configurations while maintaining both motion semantics and contact-consistent interaction patterns. Our method builds on a Part-Aware Motion Embedding (PAME) autoencoder, which encodes full-body motion into a shared body-part-wise latent space. This representation enables generalization across heterogeneous skeletons while preserving local motion semantics beneficial for part-aware adaptation in HOI retargeting. On top of this representation, we introduce a contact-guided retargeting module and an object motion decoder for HOI retargeting. The contact-guided retargeting module treats the source object interaction as a condition for refining target character motion: object- and contact-related signals are encoded into a body-part-aligned latent representation and injected into decoding through a residual control branch, enabling stronger adaptation in interaction-relevant body regions without discarding the underlying motion prior. In parallel, the object motion decoder predicts a target object motion aligned with the refined target character motion, ensuring that the object trajectory remains consistent with how the interaction is realized by the target character.
CommentsSIGGRAPH Asia 2026 (Journal Track). Project page: https://cherry-leki.github.io/projects/ReCHOIR/
