On-the-fly Learning to Transfer Motion Style with Diffusion Models: A Semantic Guidance Approach

In recent years, the emergence of generative models has spurred development of human motion generation, among which the generation of stylized human motion has consistently been a focal point of research. The conventional approach for stylized human motion generation involves transferring the style from given style examples to new motions. Despite decades of research in human motion style transfer, it still faces three main challenges: 1) difficulties in decoupling the motion content and style; 2) generalization to unseen motion style. 3) requirements of dedicated motion style dataset; To address these issues, we propose an on-the-fly human motion style transfer learning method based on the diffusion model, which can learn a style transfer model in a few minutes of fine-tuning to transfer an unseen style to diverse content motions. The key idea of our method is to consider the denoising process of the diffusion model as a motion translation process that learns the difference between the style-neutral motion pair, thereby avoiding the challenge of style and content decoupling. Specifically, given an unseen style example, we first generate the corresponding neutral motion through the proposed Style-Neutral Motion Pair Generation module. We then add noise to the generated neutral motion and denoise it to be close to the style example to fine-tune the style transfer diffusion model. We only need one style example and a text-to-motion dataset with predominantly neutral motion (e.g. HumanML3D). The qualitative and quantitative evaluations demonstrate that our method can achieve state-of-the-art performance and has practical applications.