InterLCM restores low-quality faces by feeding them into a latent consistency model as an intermediate step, combining visual and spatial guidance to beat prior restoration methods with faster inference.
Generative adversarial nets.Advances in neural information processing systems, 27,
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
-
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration
InterLCM restores low-quality faces by feeding them into a latent consistency model as an intermediate step, combining visual and spatial guidance to beat prior restoration methods with faster inference.