A rectified flow matching model with an online preference optimization loop outperforms prior text-to-motion systems on HumanML3D while generating motions in about 5 milliseconds.
In Proceedings of the IEEE con- ference on computer vision and pattern recognition , 6158– 6166
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment
A rectified flow matching model with an online preference optimization loop outperforms prior text-to-motion systems on HumanML3D while generating motions in about 5 milliseconds.