MorphoStyle：具有形态控制的运动风格迁移
MorphoStyle: Motion Style Transfer with Morphology Control
- University of Edinburgh（爱丁堡大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MorphoStyle提出一种基于FSQ-VAE的形状感知运动风格迁移框架，通过对比风格编码、文本引导路由和低秩调制实现形状与风格解耦，在基准上优于现有方法。
AI中文摘要：
人体运动可以被视为动作内容、风格和身体形态的组合。现有的运动风格迁移方法在假设标准身体形态的前提下，将参考风格迁移到内容运动上，而形状感知的运动生成器则在没有显式风格控制的情况下，使运动适应目标形状。这种运动风格与形状（形态）的分离使得为非标准身体生成风格化运动变得困难；简单地将风格迁移模块与形状感知生成器结合，常常会泄漏风格参考中的动作内容，并破坏形状一致的动力学。我们提出了MorphoStyle，一个基于形状条件的有限标量量化变分自编码器（FSQ-VAE）的形状感知运动风格迁移框架。关键贡献在于将期望的风格迁移视为模块化的潜在解缠，包括：（i）一个对比风格编码器，提取与内容解耦的风格嵌入；（ii）一个文本引导的风格路由机制，在文本-运动特征空间中定位风格相关关节；（iii）一个保持流形的风格调制器，将判别性风格嵌入作为时间门控的低秩偏移注入内容特征。在基准数据集上的大量实验表明，MorphoStyle在形状控制和运动风格迁移方面均优于竞争基线，同时提供定量的形状控制。更多详情，请参见项目网站：this https URL。
英文摘要：
Human motion may be viewed as a combination of action content, style, and body morphology. Existing motion style transfer methods transfer a reference style onto a content motion while assuming a canonical body, whereas shape-aware motion generators adapt motion to a target shape without explicit style control. This separation of motion style and shape (morphology) makes it difficult to generate stylized motions for non-canonical bodies; naively combining a style transfer module with a shape-aware generator often leaks action content from the style reference and disrupts shape-consistent kinematics. We present MorphoStyle, a framework for shape-aware motion style transfer that is built on a shape-conditioned Finite-Scalar-Quantization Variational Auto-Encoder (FSQ-VAE). The key contribution is to pose the desired style transfer as modular latent disentanglement comprising: (i) a contrastive style encoder that extracts content-decoupled style embeddings; (ii) a text-guided style-routing mechanism that locates style-relevant joints in a text-motion feature space; and (iii) a manifold preserving style modulator that injects discriminative style embeddings in content features as a temporally-gated low-rank offset. Extensive experiments on benchmark datasets demonstrate that MorphoStyle outperforms competing baselines in terms of both shape control and motion style transfer, while simultaneously providing quantitative shape control. For more details, please see project website: https://github.com/funkdub/MorphoStyle.
