AI Paper Atlas

Research map / Image generation / Editing and style transfer

Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model

Baris Gecer, Binod Bhattarai, Josef Kittler, Tae-Kyun Kim

ECCV 2018 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 65 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 identity preservation loss L_C (ablation)Face generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.01: 0.50532 -> 0.53507Improved
add identity preservation loss L_C (ablation)Face generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.001: 0.17636 -> 0.18768Improved
add adversarial pair matching L_DP (ablation)Face generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.01: 0.48034 -> 0.53507Improved
add adversarial pair matching L_DP (ablation)Face generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.001: 0.15300 -> 0.18768Improved
add cycle consistency loss L_cyc (ablation)Face generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.01: 0.49701 -> 0.53507Improved
add cycle consistency loss L_cyc (ablation)Face generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.001: 0.18341 -> 0.18768No clear effect
add GANFaces synthetic images to 50% of VGG Face training dataFace generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.01: 0.49751 -> 0.53507Improved
add GANFaces synthetic images to 50% of VGG Face training dataFace generation framework (VGG 50% + GANFaces) · IJB-A verification (VGG 50% training data)TAR @ FAR=0.001: 0.17580 -> 0.18768Improved
add GANFaces synthetic images to full VGG Face training dataVGG19 face recognition · LFW verificationaccuracy (%): 94.8 -> 94.9Improved
add GANFaces synthetic images to full VGG Face training dataVGG19 face recognition · LFW verification100% - EER: 94.6 -> 95.1Improved

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