AI Paper Atlas

Research map / Image generation / GANs

Lifespan Age Transformation Synthesis

Roy Or-El, Soumyadip Sengupta, Ohad Fried, Eli Shechtman, Ira Kemelmacher-Shlizerman

ECCV 2020 · Image generation › GANs · approach: GAN-based image manipulation · 141 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 the proposed model instead of IPCGAN (CACD)Lifespan age transformation · User study vs IPCGAN CACDOverall better (count): 27 -> 120Improved
use the proposed model instead of IPCGAN (CACD) for age accuracyLifespan age transformation · User study vs IPCGAN CACDAge difference (years): 22.6 -> 11.3Improved
use the proposed model instead of IPCGAN (CACD) for identityLifespan age transformation · User study vs IPCGAN CACDSame identity (count): 150 -> 136Hurt
use the proposed model instead of PyGANLifespan age transformation · User study vs PyGAN (50-69)Overall better (count): 4 -> 16Improved
use the proposed model instead of PyGAN for age accuracyLifespan age transformation · User study vs PyGAN (50-69)Age difference (years): 23.1 -> 6.9Improved
use the proposed model instead of IPCGAN retrained on FFHQ-AgingLifespan age transformation · User study vs retrained IPCGANOverall better (count): 7 -> 142Improved
use the proposed model instead of IPCGAN retrained on FFHQ-Aging for identityLifespan age transformation · User study vs retrained IPCGANSame identity (count): 120 -> 137Improved
use the proposed model instead of IPCGAN retrained on FFHQ-Aging for age accuracyLifespan age transformation · User study vs retrained IPCGANAge difference (years): 5.9 -> 6.0No clear effect
use the proposed model instead of STGAN retrained on FFHQ-AgingLifespan age transformation · User study vs retrained STGANOverall better (count): 21 -> 123Improved
use the proposed model instead of STGAN retrained on FFHQ-Aging for age accuracyLifespan age transformation · User study vs retrained STGANAge difference (years): 15.6 -> 7.8Improved
add intermediate anchor age classes (2 -> 3 -> 6 anchors) (ablation)Lifespan age transformation · Latent interpolation (qualitative)interpolation quality (visual)Improved
represent each age class with 50 vector elements instead of 1 (ablation)Lifespan age transformation · Latent interpolation (qualitative)interpolation quality (visual)Improved

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