Efficient Text-driven Motion Generation via Latent Consistency Training

TL;DR

This paper introduces MLCT, a novel framework for efficient text-driven human motion generation that precomputes diffusion trajectories during training, enabling fast inference with minimal computational overhead.

Contribution

The paper proposes a motion autoencoder with quantization, classifier-free guidance, and a clustering guidance module to improve efficiency and consistency in motion generation.

Findings

Outperforms traditional methods in efficiency and cost

Achieves stable training in non-pixel and latent spaces

Matches state-of-the-art performance with lower inference costs

Abstract

Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing advances face significant efficiency challenges due to the substantial computational overhead of iteratively solving for nonlinear reverse diffusion trajectories during the inference phase. To this end, we propose the motion latent consistency training framework (MLCT), which precomputes reverse diffusion trajectories from raw data in the training phase and enables few-step or single-step inference via self-consistency constraints in the inference phase. Specifically, a motion autoencoder with quantization constraints is first proposed for constructing concise and bounded solution distributions for motion diffusion processes. Subsequently, a classifier-free guidance format is constructed via an additional unconditional loss function to accomplish the precomputation of conditional diffusion trajectories in the training phase. Finally, a clustering guidance module based on the K-nearest-neighbor algorithm is developed for the chain-conduction optimization mechanism of self-consistency constraints, which provides additional references of solution distributions at a small query cost. By combining these enhancements, we achieve stable and consistency training in non-pixel modality and latent representation spaces. Benchmark experiments demonstrate that our method significantly outperforms traditional consistency distillation methods with reduced training cost and enhances the consistency model to perform comparably to state-of-the-art models with lower inference costs.