Momentum Flow perturbs rectified flow velocities with a decaying random component and shows improved FID and recall on CelebA-HQ with half the sampling steps.
Neural flow diffusion models: Learnable forward process for improved diffusion modelling.Advances in Neural Information Processing Systems, 37:73952–73985, 2024
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
background 1representative citing papers
citing papers explorer
-
Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Sampling
Momentum Flow perturbs rectified flow velocities with a decaying random component and shows improved FID and recall on CelebA-HQ with half the sampling steps.