AI Paper Atlas

Research map / Image generation / GANs

Disentangled Inference for GANs With Latently Invertible Autoencoder

Jiapeng Zhu, Deli Zhao, Bo Zhang, Bolei Zhou

IJCV 2022 · Image generation › GANs · approach: Large-scale GAN latent analysis · 36 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 y-space (after mapping network) instead of z-space for interpolationStyleGAN · FFHQperceptual path length: 40.25 -> 23.26Improved
add invertible network in place of the MLP mapping (LIA/GAN vs VAE/GAN) (ablation)StyleGAN encoder · FFHQ reconstructionFID: 22.26 -> 19.26Improved
add invertible network in place of the MLP mapping (LIA/GAN vs VAE/GAN) (ablation)StyleGAN encoder · FFHQ reconstructionMSE: 23.18 -> 11.79Improved
add invertible network in place of the MLP mapping (LIA/GAN vs VAE/GAN) (ablation)StyleGAN encoder · FFHQ reconstructionSWD: 15.82 -> 12.16Improved
use LIA encoder instead of MSE-based GAN inversionStyleGAN · FFHQ reconstructionFID: 44.79 -> 19.26Improved
use LIA encoder instead of ALI adversarial inferenceStyleGAN · FFHQ reconstructionMSE: 32.61 -> 11.79Improved
initialize finetuning from LIA encoder output instead of average y (ablation)latent finetuning · FFHQ last 1,000 imagesFID: 57.09 -> 39.52Improved
initialize finetuning from LIA encoder output instead of random sampling (ablation)latent finetuning · FFHQ last 1,000 imagesFID: 105.52 -> 39.52Improved
initialize finetuning from LIA encoder output instead of average y (ablation)latent finetuning · FFHQ last 1,000 imagesPSNR: 19.33 -> 23.51Improved
optimize in disentangled y-space instead of z-space (encoder init) (ablation)latent finetuning · Web images (100)MSE: 0.0319 -> 0.0055Improved
optimize in y-space instead of z-space (random init) (ablation)latent finetuning · Web images (100)FID: 216.8 -> 75.34Improved
optimize in y-space instead of z-space (average init) (ablation)latent finetuning · Web images (100)MSE: 0.058 -> 0.0075Improved

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