AI Paper Atlas

Research map / Image generation / GANs

Linearly Controllable GAN: Unsupervised Feature Categorization and Decomposition for Image Generation and Manipulation

sehyung lee, Mijung Kim, Yeongnam Chae, Bjorn Stenger

ECCV 2024 · Image generation › GANs · approach: Large-scale GAN latent analysis · 4 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 contrastive loss and spectral regularization to generator training (ablation)LC-GAN · CelebA-HQ 256 and FFHQ 256FID: 3.54 / 3.66 (ablated) vs 3.72 (full) on CA-L; 3.30 / 3.45 vs 3.65 on FF-LNo clear effect
add spectral regularization on top of contrastive loss (ablation)LC-GAN · FFHQ 256 latent controlnumber of dimensions to edit per attribute (qualitative)Improved
add contrastive feature categorization into geometry and appearance codes (ablation)LC-GAN · FFHQ 256 latent controldisentanglement (qualitative)Improved
use LC-GAN latent control instead of SeFa and EigenGAN for viewpoint changeLC-GAN · CelebA-HQ 1024 and FFHQ 1024Arcface distance: 0.71 vs 0.91 (SeFa), 0.99 (EigenGAN) at CA-L; 0.61 vs 1.13, 0.99 at FF-HImproved
use LC-GAN instead of SeFa and EigenGAN for appearance changeLC-GAN · CelebA-HQ 1024Landmark distance: 5.83 vs 10.42 (SeFa), 13.46 (EigenGAN)Improved
LC-GAN versus uncontrollable StyleNAT at 256 resolution FFHQLC-GAN · FFHQ 256x256FID: 3.65 vs 2.05 (StyleNAT)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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