pith. sign in

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 1

years

2026 1

verdicts

UNVERDICTED 1

roles

baseline 1

polarities

baseline 1

representative citing papers

Improving Human Image Animation via Semantic Representation Alignment

cs.CV · 2026-05-11 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Improving Human Image Animation via Semantic Representation Alignment cs.CV · 2026-05-11 · unverdicted · none · ref 10

    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.