SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization

TL;DR

This paper introduces SoPo, a semi-online preference optimization method for text-to-motion generation that combines online and offline data to improve motion quality and preference alignment, outperforming existing methods.

Contribution

We propose a novel semi-online DPO-based approach that addresses limitations of purely online or offline methods for text-to-motion generation.

Findings

SoPo outperforms other preference alignment methods in experiments.

The MLD model fine-tuned by SoPo surpasses state-of-the-art models.

Visualization confirms effective preference alignment by SoPo.

Abstract

Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fine-tuning text-to-motion models to consistently favor high-quality, human-preferred motions, a critical yet largely unexplored problem. In this work, we theoretically investigate the DPO under both online and offline settings, and reveal their respective limitation: overfitting in offline DPO, and biased sampling in online DPO. Building on our theoretical insights, we introduce Semi-online Preference Optimization (SoPo), a DPO-based method for training text-to-motion models using "semi-online" data pair, consisting of unpreferred motion from online distribution and preferred motion in offline datasets. This method leverages both online and offline DPO, allowing each to compensate for the other's limitations. Extensive experiments demonstrate that SoPo outperforms other preference alignment methods, with an MM-Dist of 3.25% (vs e.g. 0.76% of MoDiPO) on the MLD model, 2.91% (vs e.g. 0.66% of MoDiPO) on MDM model, respectively. Additionally, the MLD model fine-tuned by our SoPo surpasses the SoTA model in terms of R-precision and MM Dist. Visualization results also show the efficacy of our SoPo in preference alignment. Project page: https://xiaofeng-tan.github.io/projects/SoPo/ .