RecMoDiffuse: Recurrent Flow Diffusion for Human Motion Generation
This work addresses motion incoherence and computational inefficiency in human motion generation for computer animation, representing an incremental improvement over existing diffusion-based methods.
The paper tackles the problem of generating coherent, long-duration human motion sequences by proposing RecMoDiffuse, a recurrent diffusion method that integrates normalizing flows to enforce temporal constraints, achieving comparable results to state-of-the-art methods with reduced computational overhead.
Human motion generation has paramount importance in computer animation. It is a challenging generative temporal modelling task due to the vast possibilities of human motion, high human sensitivity to motion coherence and the difficulty of accurately generating fine-grained motions. Recently, diffusion methods have been proposed for human motion generation due to their high sample quality and expressiveness. However, generated sequences still suffer from motion incoherence, and are limited to short duration, and simpler motion and take considerable time during inference. To address these limitations, we propose \textit{RecMoDiffuse: Recurrent Flow Diffusion}, a new recurrent diffusion formulation for temporal modelling. Unlike previous work, which applies diffusion to the whole sequence without any temporal dependency, an approach that inherently makes temporal consistency hard to achieve. Our method explicitly enforces temporal constraints with the means of normalizing flow models in the diffusion process and thereby extends diffusion to the temporal dimension. We demonstrate the effectiveness of RecMoDiffuse in the temporal modelling of human motion. Our experiments show that RecMoDiffuse achieves comparable results with state-of-the-art methods while generating coherent motion sequences and reducing the computational overhead in the inference stage.