TSTMotion is a training-free framework that uses LLM-generated skeleton guidance and two gradient losses to make blank-background motion diffusion models produce scene-aware, text-driven motions.
Humanise: Language-conditioned human motion generation in 3d scenes,
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
-
TSTMotion: Training-free Scene-aware Text-to-motion Generation
TSTMotion is a training-free framework that uses LLM-generated skeleton guidance and two gradient losses to make blank-background motion diffusion models produce scene-aware, text-driven motions.