MOVi improves multi-object video generation without retraining by using LLM-planned trajectories to reinitialize the diffusion noise and by reweighting attention to stop objects from mixing together.
Videocrafter2: Overcoming data limitations for high- quality video diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
MOVi: Training-free Text-conditioned Multi-Object Video Generation
MOVi improves multi-object video generation without retraining by using LLM-planned trajectories to reinitialize the diffusion noise and by reweighting attention to stop objects from mixing together.