MotionDuet generates realistic controllable 3D human motions via dual text-video conditioning with DUET unified encoding and DASH distribution-aware loss.
Deepphase: Periodic autoencoders for learning motion phase manifolds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MotionDuet: Dual-Conditioned 3D Human Motion Generation with Video-Regularized Text Learning
MotionDuet generates realistic controllable 3D human motions via dual text-video conditioning with DUET unified encoding and DASH distribution-aware loss.