VQ-Style:通过残差量化表示解构运动中的风格与内容
VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
AI总结:
本文提出VQ-Style方法,通过残差量化表示解构运动中的风格与内容,实现无需微调的风格迁移和多种运动应用。
摘要:
人类运动数据本质上丰富而复杂,包含既有语义内容又含细微风格特征,这些特征具有挑战性。我们提出了一种新的方法,以有效解构人类运动数据中的风格和内容,以促进风格迁移。我们的方法基于内容对应于粗略运动属性,而风格捕捉更细致的表达细节的洞察。为了建模这种层次结构,我们采用残差向量量化变分自编码器(RVQ-VAEs)来学习从粗到细的运动表示。我们进一步通过整合代码本学习与对比学习以及一种新的信息泄漏损失来增强解构,以在不同代码本之间组织内容和风格。我们利用这种解构的表示,通过我们的简单而有效的推理时间技术量化代码交换,使运动风格迁移无需对未见过的风格进行微调。我们的框架在多个推理应用中表现出强大的适应性,包括风格迁移、风格去除和运动融合。
英文摘要:
Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion data to facilitate style transfer. Our approach is guided by the insight that content corresponds to coarse motion attributes while style captures the finer, expressive details. To model this hierarchy, we employ Residual Vector Quantized Variational Autoencoders (RVQ-VAEs) to learn a coarse-to-fine representation of motion. We further enhance the disentanglement by integrating codebook learning with contrastive learning and a novel information leakage loss to organize the content and the style across different codebooks. We harness this disentangled representation using our simple and effective inference-time technique Quantized Code Swapping, which enables motion style transfer without requiring any fine-tuning for unseen styles. Our framework demonstrates strong versatility across multiple inference applications, including style transfer, style removal, and motion blending.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。