Flow Matching for Realistic Text-Driven Human Motion Generation
Achieving highly diverse and perceptually consistent 3D character animations with natural motion and low computational costs remains a challenge in computer animation. Existing methods often struggle to provide the nuanced complexity of human movement, resulting in perceptual inconsistencies and motion artifacts. To tackle these issues, we introduce FlowMotion, a novel approach that leverages Conditional Flow Matching (CFM) for improved motion synthesis. FlowMotion incorporates an innovative training objective that more accurately predicts target motion, reducing the inherent jitter associated with CFM while enhancing stability, realism, and computational efficiency in generating animations. This direct prediction approach enhances the perceptual quality of animations by reducing erratic motion and aligning the training more closely with the dynamic characteristics of human movement. Our preliminary experimental results demonstrate that FlowMotion achieves higher balance between motion smoothness and generalization capability while maintaining the computational efficiency inherent in flow matching compared to state-of-the-art methods.