SemanticREPA aligns structure representations from video latents with depth features and ID representations with face recognition features to supervise diffusion models, yielding more coherent and consistent human animations.
Seine: Short-to-long video diffusion model for generative transition and prediction
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
2026 1verdicts
UNVERDICTED 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Improving Human Image Animation via Semantic Representation Alignment
SemanticREPA aligns structure representations from video latents with depth features and ID representations with face recognition features to supervise diffusion models, yielding more coherent and consistent human animations.