UniTemp enables arbitrary temporal order video generation in autoregressive diffusion models via bidirectional distillation and blockwise anchor latents.
Multicoin: Multi-modal controllable video inbe- tweening
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
VHOI densifies sparse trajectories into color-encoded HOI mask sequences and conditions a fine-tuned video diffusion model on them to produce controllable human-object interaction videos, including full navigation sequences.
citing papers explorer
-
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
UniTemp enables arbitrary temporal order video generation in autoregressive diffusion models via bidirectional distillation and blockwise anchor latents.
-
VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification
VHOI densifies sparse trajectories into color-encoded HOI mask sequences and conditions a fine-tuned video diffusion model on them to produce controllable human-object interaction videos, including full navigation sequences.