Model
Gan : Generative Adversarial Networks [paper]
DCGan : Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [paper]
PGGan : Progressive Growing of GANs for Improved Quality, Stability, and Variation [paper]
StyleGan : A Style-Based Generator Architecture for Generative Adversarial Networks [paper]
StyleGan2 : Analyzing and Improving the Image Quality of StyleGAN [paper]
StyleGan-ada : Training Generative Adversarial Networks with Limited Data [paper]
StyleGan3 : Alias-Free Generative Adversarial Networks [paper]
Inversion
Image2StyleGan : Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?[paper]
Image2StyleGan++ :Image2StyleGAN++: How to Edit the Embedded Images?[paper]
IDInvert : In-Domain GAN Inversion for Real Image Editing [paper]
pSp : Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation [paper]
StyleSpace : StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation [paper]
e4e : Designing an Encoder for StyleGAN Image Manipulation [paper]
ReStyle : A Residual-Based StyleGAN Encoder via Iterative Refinement [paper]
PTI : Pivotal Tuning for Latent-based Editing of Real Images [paper]
HyperStyle : StyleGAN Inversion with HyperNetworks for Real Image Editing [paper]
Stylegan3-inversion : Third Time's the Charm? Image and Video Editing with StyleGAN3 [paper]
Manipulation
- Supervised Linear approach
InterfaceGan : Interpreting the Disentangled Face Representation Learned by GANs [paper]
- find hyperplane of binary-attribute
HiGan : Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis[paper]
- Unsupervised Linear approach
Unsupervised discovery of interpretable directions in the gan latent space [paper]
GanSpace : Discovering Interpretable GAN Controls [paper]
SeFa : Closed-Form Factorization of Latent Semantics in GANs [paper]
- Non-Linear approach
StyleFlow : Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows [paper]
DyStyle : Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing [paper]
- other methods
StyleRig : Rigging StyleGAN for 3D Control over Portrait Images [paper]
StyleganRender : Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering [paper]
FreeStyleGan : Free-view Editable Portrait Rendering with the Camera Manifold [paper]
StyleClip : Text-Driven Manipulation of StyleGAN Imagery [paper]
TargetClip : Image-Based CLIP-Guided Essence Transfer [paper]
Clip2Stylegan : Unsupervised Extraction of StyleGAN Edit Directions [paper]
- finer control
Pose with Style : Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN [paper]
StyleMapGan : Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing [paper]
fine-tunning generator
Stylegan-NADA
AgileGan
Mind the Gap
BlendGan
