PCFlow combines latent consistency flow matching, a perceptual loss between adjacent-step predictions, and asymmetric gradient projection to achieve fast few-step image restoration with improved FID but reduced distortion fidelity.
Advances in Neural Information Processing Systems36, 61777–61791 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
PCFlow combines latent consistency flow matching, a perceptual loss between adjacent-step predictions, and asymmetric gradient projection to achieve fast few-step image restoration with improved FID but reduced distortion fidelity.