VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
Goku: Flow based video generative foundation models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative 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.
TM outperforms FM for well-separated modes with non-negligible variance by preserving covariance via stochastic latent updates, with the gap closing as variance approaches zero.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
VACE: All-in-One Video Creation and Editing
VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
-
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.
-
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
TM outperforms FM for well-separated modes with non-negligible variance by preserving covariance via stochastic latent updates, with the gap closing as variance approaches zero.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.