GAN Inversion: A Survey

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. As an emerging technique to bridge the real and fake image domains, GAN inversion plays an essential role in enabling the pretrained GAN models such as StyleGAN and BigGAN to be used for real image editing applications... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions
Dot-Product Attention
Attention Mechanisms
SAGAN Self-Attention Module
Attention Modules
Adam
Stochastic Optimization
Off-Diagonal Orthogonal Regularization
Regularization
Non-Local Operation
Image Feature Extractors
GAN Hinge Loss
Loss Functions
Dense Connections
Feedforward Networks
SAGAN
Generative Adversarial Networks
1x1 Convolution
Convolutions
Truncation Trick
Latent Variable Sampling
Projection Discriminator
Discriminators
ReLU
Activation Functions
Batch Normalization
Normalization
Early Stopping
Regularization
Residual Connection
Skip Connections
TTUR
Optimization
Linear Layer
Feedforward Networks
Residual Block
Skip Connection Blocks
Conditional Batch Normalization
Normalization
Non-Local Block
Image Model Blocks
Spectral Normalization
Normalization
BigGAN
Generative Models
Convolution
Convolutions
Feedforward Network
Feedforward Networks
Adaptive Instance Normalization
Normalization
Leaky ReLU
Activation Functions
R1 Regularization
Regularization
StyleGAN
Generative Models