Video-pretrained diffusion features beat matched image-pretrained features on most perception tasks, with the largest gains on motion and geometry tasks, but still trail contrastive models on semantics.
Video diffusion models learn the struc- ture of the dynamic world
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
-
From Image to Video: An Empirical Study of Diffusion Representations
Video-pretrained diffusion features beat matched image-pretrained features on most perception tasks, with the largest gains on motion and geometry tasks, but still trail contrastive models on semantics.