AI Paper Atlas

Research map / Image generation / GANs

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement

Yuval Alaluf, Or Patashnik, Daniel Cohen-Or

ICCV 2021 · Image generation › GANs · approach: Large-scale GAN latent analysis · 329 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
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Faces (1024)runtime: 0.538 -> 0.451Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Faces (1024)MSE: 0.14 -> 0.13Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Faces (1024)LPIPS: 0.03 -> 0.03No clear effect
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Cars (512)LPIPS: 0.08 -> 0.07Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Cars (512)runtime: 0.411 -> 0.361Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · AFHQ Wild (512)MSE: 0.23 -> 0.21Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · AFHQ Wild (512)LPIPS: 0.06 -> 0.06No clear effect
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Churches (256)MSE: 0.28 -> 0.26Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Churches (256)runtime: 0.355 -> 0.298Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Horses (256)MSE: 0.32 -> 0.31Improved
use simplified encoder (all styles from final 16x16 feature map) instead of FPN-based encoder (ablation)ReStyle over pSp · Horses (256)LPIPS: 0.09 -> 0.09No clear effect
train a dedicated residual iterative scheme (input plus current output, predict residual) instead of repeatedly feeding output of a pre-trained pSp/e4e encoder (ablation)ReStyle over pSp · pSp and e4eFFHQ faces and Stanford Cars reconstruction over stepsImproved

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