HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback
This enables personalized and style-aware human motion generation with reduced human effort, though it is incremental as it builds on latent diffusion models.
The paper tackles generating natural human motions by adapting latent motion diffusion models with minimal human feedback, achieving performance comparable to extensive feedback and significantly outperforming existing state-of-the-art methods.
We introduce HuTuMotion, an innovative approach for generating natural human motions that navigates latent motion diffusion models by leveraging few-shot human feedback. Unlike existing approaches that sample latent variables from a standard normal prior distribution, our method adapts the prior distribution to better suit the characteristics of the data, as indicated by human feedback, thus enhancing the quality of motion generation. Furthermore, our findings reveal that utilizing few-shot feedback can yield performance levels on par with those attained through extensive human feedback. This discovery emphasizes the potential and efficiency of incorporating few-shot human-guided optimization within latent diffusion models for personalized and style-aware human motion generation applications. The experimental results show the significantly superior performance of our method over existing state-of-the-art approaches.