Methods › Computer Vision › Face Restoration Models

Face Restoration Models

5 methods 8 papers tagged archive 2025-07-28

Generative Adversarial Networks (GANs) are a type of generative model that use two networks, a generator to generate images and a discriminator to discriminate between real and fake, to train a model that approximates the distribution of the data. Below you can find a continuously updating list of GANs.

Methods

All 5 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

GFP-GAN – 3
ISPL Implicit Subspace Prior Learning – 3
DFDNet – 1
PSFR-GAN – 1
WIPA Wavelet-integrated Identity Preserving Adversarial Network for face super-resolution – 0