MoST：不同动作内容之间的运动风格Transformer
MoST: Motion Style Transformer between Diverse Action Contents
AI总结：
提出MoST运动风格Transformer，通过跨身体部件的部分注意力风格调制器、Siamese编码器和风格解耦损失实现内容与风格解耦，有效解决不同内容运动间的风格迁移问题，无需启发式后处理且性能优于现有方法。
摘要：
尽管现有的运动风格迁移方法在内容相同的两个运动之间很有效，但当在不同内容的运动之间迁移风格时，其性能会显著下降。这一挑战在于运动的内容与风格之间缺乏明确的分离。为了应对这一挑战，我们提出了一种新颖的运动风格Transformer，它能有效地将风格从内容中解耦，并从源运动生成具有迁移风格的合理运动。我们实现解耦目标的独特方法是双重的：（1）一种新的运动风格Transformer架构，包含“跨身体部件的部分注意力风格调制器”和“分别编码风格和内容特征的Siamese编码器”；（2）风格解耦损失。我们的方法优于现有方法，并展现出极高的质量，特别是在不同内容的运动对中，无需启发式后处理。代码可在 https://github.com/Boeun-Kim/MoST 获取。
英文摘要：
While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents. This challenge lies in the lack of clear separation between content and style of a motion. To tackle this challenge, we propose a novel motion style transformer that effectively disentangles style from content and generates a plausible motion with transferred style from a source motion. Our distinctive approach to achieving the goal of disentanglement is twofold: (1) a new architecture for motion style transformer with `part-attentive style modulator across body parts' and `Siamese encoders that encode style and content features separately'; (2) style disentanglement loss. Our method outperforms existing methods and demonstrates exceptionally high quality, particularly in motion pairs with different contents, without the need for heuristic post-processing. Codes are available at https://github.com/Boeun-Kim/MoST.
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。
