AI Paper Atlas

Research map / Image generation / GANs

In-Domain GAN Inversion for Faithful Reconstruction and Editability

Jiapeng Zhu, Yujun Shen, Yinghao Xu, Deli Zhao, Qifeng Chen, Bolei Zhou

TPAMI 2024 · Image generation › GANs · approach: Large-scale GAN latent analysis · 15 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
add w average to the encoder output (ablation)Domain-guided encoder · FFHQ inversion (StyleGAN2)FID: 27.95 -> 14.93Improved
add w average to the encoder output (ablation)Domain-guided encoder · FFHQ inversion (StyleGAN2)MSE: 0.074 -> 0.036Improved
add w average (ablation)Domain-guided encoder · FFHQ interpolation (StyleGAN2)FID: 70.69 -> 52.52Improved
retrain generator with enlarged W+ space (ablation)Encoder · FFHQ reconstruction (StyleGAN)MSE: 0.061 -> 0.053Improved
retrain generator with enlarged W+ space (ablation)Encoder · FFHQ interpolation (StyleGAN)FID: 44.97 -> 46.56Hurt
retrain generator with enlarged W+ space (ablation)Encoder · FFHQ (StyleGAN2)FID: reconstruction 15.30 -> 14.93, interpolation 50.46 -> 52.52Mixed
use ResNet-50 encoder instead of base encoder (ablation)Domain-guided encoder · FFHQ inversionSWD: 13.02 -> 7.31Improved
use MobileNet encoder instead of base (ablation)Domain-guided encoder · FFHQ inversionFID: 16.43 -> 17.11Hurt
use ResNet-34 instead of base encoder (ablation)Domain-guided encoder · LSUN Church inversionFID: 12.06 -> 11.18Improved
replace noise at later generator blocks (ablation)Generator · FFHQFID: 41.89 -> 58.26Hurt
add in-domain optimization on top of domain-guided encoderIn-Domain Inversion · FFHQ inversionSSIM: 0.522 -> 0.568Improved
domain-guided encoder vs Image2StyleGANIn-Domain Inversion · FFHQ inversionFID: 25.35 -> 15.07Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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