A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
Photorealistic video generation with diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Frozen Forecasting: A Unified Evaluation
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.