atlas

Research map / Image generation / GANs

Continuous Face Aging via Self-Estimated Residual Age Embedding

CVPR 2021 · Image generation › GANs · approach: GAN-based image manipulation · 37 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 self-estimated continuous age embeddings instead of interpolation between anchor age groupsFace aging · FFHQ, continuous agingaging accuracyHelped
Use personalized residual age embedding in the target age embedding (ablation)Continuous face aging model · Face aging examplespersonalized trait preservation and visual artifactsHelped
Add the target-age shift coefficient βφ (ablation)Personalized age embedding transformation · Face agingperformanceNo clear effect
Use the proposed method rather than S²GANFace aging · CACD2000face verification rate: 98.91% -> 99.97%Helped
Use the proposed method rather than LifespanFace aging · FFHQface verification rate: 87.11% -> 99.98%Helped
Use the proposed method rather than S²GANFace aging · CACD2000FID: 8.4 -> 6.7Helped
Use the proposed method rather than LifespanFace aging · FFHQFID: 26.2 -> 18.5Helped
Use the proposed method rather than LifespanFace aging · FFHQ age group 30-39mean generated age: 38.4 -> 38.4No clear effect

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