AI Paper Atlas

Research map / Image generation / Editing and style transfer

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?

Rameen Abdal, Yipeng Qin, Peter Wonka

ICCV 2019 · Image generation › Editing and style transfer · approach: GAN inversion for editing · 1,090 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
initialize with mean latent instead of random (ablation)embedding · Face imagesloss L (x10^5): 0.351 -> 0.309Improved
initialize with mean latent instead of random (ablation)embedding · Face imagesdistance to mean latent: 35.60 -> 30.67Improved
initialize with mean latent instead of random (ablation)embedding · Dog imagesloss L (x10^5): 0.845 -> 0.922Hurt
initialize with mean latent instead of random (ablation)embedding · Cat imagesloss L (x10^5): 0.740 -> 0.752No clear effect
initialize with mean latent instead of random (ablation)embedding · Painting imagesloss L (x10^5): 3.451 -> 3.530Hurt
initialize with mean latent instead of random (ablation)embedding · Car imagesloss L (x10^5): 1.269 -> 1.390Hurt
embed into extended latent space W+ instead of W (ablation)StyleGAN embedding · Face and other imagesqualitative embedding qualityImproved
add multi-layer VGG perceptual loss instead of single layer (ablation)embedding loss · Five image classesqualitative embedding qualityImproved
add perceptual loss to pixel-wise MSE loss (ablation)embedding loss · Five image classesqualitative embedding qualityImproved
apply perceptual loss on images resized to 256x256 (ablation)embedding loss · 1024x1024 imagesqualitative embedding qualityImproved
resample noise at each update step instead of keeping it constant (ablation)embedding · Face and other imagesqualitative embedding qualityHurt
use pretrained FFHQ weights instead of random weights (ablation)embedding · Face and other imagesqualitative embedding qualityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy