MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment
This addresses the need for efficient and accurate motion generation for animating virtual characters and embodied agents, representing a significant incremental improvement over existing methods.
The paper tackles the problem of inefficient and imprecise text-guided motion generation by introducing TAPO for semantic alignment and MotionFLUX for real-time synthesis, achieving state-of-the-art performance in semantic consistency and motion quality with accelerated generation speed.
Motion generation is essential for animating virtual characters and embodied agents. While recent text-driven methods have made significant strides, they often struggle with achieving precise alignment between linguistic descriptions and motion semantics, as well as with the inefficiencies of slow, multi-step inference. To address these issues, we introduce TMR++ Aligned Preference Optimization (TAPO), an innovative framework that aligns subtle motion variations with textual modifiers and incorporates iterative adjustments to reinforce semantic grounding. To further enable real-time synthesis, we propose MotionFLUX, a high-speed generation framework based on deterministic rectified flow matching. Unlike traditional diffusion models, which require hundreds of denoising steps, MotionFLUX constructs optimal transport paths between noise distributions and motion spaces, facilitating real-time synthesis. The linearized probability paths reduce the need for multi-step sampling typical of sequential methods, significantly accelerating inference time without sacrificing motion quality. Experimental results demonstrate that, together, TAPO and MotionFLUX form a unified system that outperforms state-of-the-art approaches in both semantic consistency and motion quality, while also accelerating generation speed. The code and pretrained models will be released.