StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework

TL;DR

StableMoFusion is a new diffusion-based framework for human motion generation that improves efficiency and robustness by analyzing and tailoring network components, while also addressing foot skating issues through contact-aware corrections.

Contribution

It provides a comprehensive analysis of diffusion model components and introduces tailored designs for efficient, high-quality motion generation with foot skating correction.

Findings

Outperforms current state-of-the-art methods in human motion generation

Reduces computational overhead for real-time applications

Effectively eliminates foot skating in generated motions

Abstract

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/