A diffusion transformer clones camera motion from a reference video by concatenating reference latent tokens into the sequence, unifying image-to-video and video-to-video camera control after training on a new synthetic dataset.
Lindell, and Sergey Tulyakov
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CamCloneMaster: Enabling Reference-based Camera Control for Video Generation
A diffusion transformer clones camera motion from a reference video by concatenating reference latent tokens into the sequence, unifying image-to-video and video-to-video camera control after training on a new synthetic dataset.