Latent-PMRF trains a rectified flow from the latent code of a posterior-mean estimate to the latent code of a high-quality face, achieving faster convergence and better perceptual quality than pixel-space PMRF.
Build- ing normalizing flows with stochastic interpolants
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent Posterior-Mean Rectified Flow for Higher-Fidelity Perceptual Face Restoration
Latent-PMRF trains a rectified flow from the latent code of a posterior-mean estimate to the latent code of a high-quality face, achieving faster convergence and better perceptual quality than pixel-space PMRF.