DFM applies flow matching with per-stage noise schedules to Laplacian pyramid levels in one shared DiT, improving FID and FDD on ImageNet and video benchmarks over prior progressive generation baselines.
Generative pretraining from pixels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Improving Progressive Generation with Decomposable Flow Matching
DFM applies flow matching with per-stage noise schedules to Laplacian pyramid levels in one shared DiT, improving FID and FDD on ImageNet and video benchmarks over prior progressive generation baselines.