A non-autoregressive diffusion framework that predicts any future frame tuple directly from context, with a motion-prediction module and an overlap-consistency training loss.
We compared the proposed AR- Free video prediction framework with several SOTA video prediction methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Autoregression-free video prediction using diffusion model for mitigating error propagation
A non-autoregressive diffusion framework that predicts any future frame tuple directly from context, with a motion-prediction module and an overlap-consistency training loss.