AI Paper Atlas

Research map / Image generation / Editing and style transfer

Image-to-Image Translation With Disentangled Latent Vectors for Face Editing

Yusuf Dalva, Hamza Pehlivan, Öykü Irmak Hatipoğlu, Cansu Moran, Ayşegül Dündar

TPAMI 2023 · Image generation › Editing and style transfer · approach: GAN inversion for editing · 41 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 orthogonality loss (ablation)VecGAN · CelebA-HQ Setting I (bangs addition, 128x128), latent-guidedFID: 21.98 -> 20.17Improved
add sparsity loss (ablation)VecGAN · CelebA-HQ Setting I (bangs addition, 128x128), latent-guidedFID: 24.07 -> 20.17Improved
add sparsity loss (ablation)VecGAN · CelebA-HQ Setting I (bangs addition, 128x128), reference-guidedFID: 22.43 -> 20.72Improved
add disentanglement loss (ablation)VecGAN · CelebA-HQ Setting I (bangs addition, 128x128), reference-guidedFID: 20.72 -> 20.57Improved
add disentanglement loss (ablation)VecGAN · CelebA-HQ Setting I (bangs addition, 128x128), latent-guidedFID: 20.17 -> 20.23No clear effect
add single-layer attention skip connection (ablation)Disent. · CelebA-HQ Setting I (bangs addition, 128x128), reference-guidedFID: 20.57 -> 20.08Improved
replace single-layer attention skip with UNet attention skip (ablation)Disent. + Attn. Skip · CelebA-HQ Setting I (bangs addition, 128x128), reference-guidedFID: 20.08 -> 19.87Improved
feed decoded features to UNet attention skip (ablation)Disent. + Attn. UNet Skip · CelebA-HQ Setting I (bangs addition, 128x128), latent-guidedFID: 19.98 -> 19.65Improved
upgrade VecGAN to VecGAN++ (disentanglement loss and attention skips)VecGAN · CelebA-HQ Setting I (bangs addition, 128x128), latent-guidedFID: 20.17 -> 19.65Improved
upgrade VecGAN to VecGAN++VecGAN · CelebA-HQ Setting II (256x256), bangs additionFID: 36.47 -> 27.09Improved
upgrade VecGAN to VecGAN++VecGAN · CelebA-HQ Setting II (256x256), gender femaleFID: 63.48 -> 30.24Improved
upgrade VecGAN to VecGAN++VecGAN · CelebA-HQ Setting II (256x256), blonde hair (+)FID: 68.89 -> 37.18Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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