Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation

TL;DR

This paper introduces RAM, a novel diffusion model for text-to-motion generation that uses motion latent space supervision and a reconstructive error guidance mechanism to improve accuracy and reduce error propagation.

Contribution

RAM combines motion latent space supervision with a reconstructive error guidance technique, advancing the state-of-the-art in text-to-motion generation.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Significantly reduces error propagation during denoising.

Improves motion generation accuracy and diversity.

Abstract

Diffusion models have seen widespread adoption for text-driven human motion generation and related tasks due to their impressive generative capabilities and flexibility. However, current motion diffusion models face two major limitations: a representational gap caused by pre-trained text encoders that lack motion-specific information, and error propagation during the iterative denoising process. This paper introduces Reconstruction-Anchored Diffusion Model (RAM) to address these challenges. First, RAM leverages a motion latent space as intermediate supervision for text-to-motion generation. To this end, RAM co-trains a motion reconstruction branch with two key objective functions: self-regularization to enhance the discrimination of the motion space and motion-centric latent alignment to enable accurate mapping from text to the motion latent space. Second, we propose Reconstructive Error Guidance (REG), a testing-stage guidance mechanism that exploits the diffusion model's inherent self-correction ability to mitigate error propagation. At each denoising step, REG uses the motion reconstruction branch to reconstruct the previous estimate, reproducing the prior error patterns. By amplifying the residual between the current prediction and the reconstructed estimate, REG highlights the improvements in the current prediction. Extensive experiments demonstrate that RAM achieves significant improvements and state-of-the-art performance. Our code will be released.