StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
This work addresses inefficiencies and quality issues in motion generation for applications like virtual characters and humanoid robots, representing an incremental improvement over existing diffusion-based methods.
The authors tackled the problem of inefficient and foot-skate-prone diffusion models for human motion generation by tailoring network architectures, training strategies, and inference processes, and introducing a foot-ground contact correction method, resulting in a framework that outperforms state-of-the-art methods in experiments.
Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The effect of the design of each component is still unclear. In addition, the iterative denoising process consumes considerable computational overhead, which is prohibitive for real-time scenarios such as virtual characters and humanoid robots. For this reason, we first conduct a comprehensive investigation into network architectures, training strategies, and inference processs. Based on the profound analysis, we tailor each component for efficient high-quality human motion generation. Despite the promising performance, the tailored model still suffers from foot skating which is an ubiquitous issue in diffusion-based solutions. To eliminate footskate, we identify foot-ground contact and correct foot motions along the denoising process. By organically combining these well-designed components together, we present StableMoFusion, a robust and efficient framework for human motion generation. Extensive experimental results show that our StableMoFusion performs favorably against current state-of-the-art methods. Project page: https://h-y1heng.github.io/StableMoFusion-page/