AI Paper Atlas

Research map / Image generation / GANs

Global Texture Enhancement for Fake Face Detection in the Wild

Zhengzhe Liu, Xiaojuan Qi, Philip H.S. Torr

CVPR 2020 · Image generation › GANs · approach: GAN-based image manipulation · 371 citations (OpenAlex)

Check 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 Gram Blocks that encode global texture featuresResNet-18 fake-face detector · StyleGAN vs. CelebA-HQ, average across in-domain, edits, and cross-GAN testsaccuracy: 88.20 -> 95.51Improved
Add Gram Blocks that encode global texture featuresResNet-18 fake-face detector · PGGAN vs. CelebA-HQ, average across settingsaccuracy: 89.45 -> 92.28Improved
Add Gram Blocks that encode global texture featuresResNet-18 fake-face detector · Low-resolution GANs (DCGAN, DRAGAN, StarGAN) vs. CelebAaccuracy: 75.11 ± 8.10 -> 81.65 ± 3.51; 65.53 ± 8.20 -> 76.40 ± 6.06; 64.04 ± 7.69 -> 74.96 ± 4.90Improved
Add Gram Blocks that encode global texture featuresResNet-18 detector trained on faces · ImageNet vs. BigGANaccuracy: 71.93 ± 2.09 -> 80.29 ± 3.20Improved
Use only cheek skin rather than the full image (ablation)ResNet-18 · In-domain StyleGAN vs. CelebA-HQaccuracy: 99.99% -> 99.93%No clear effect
Convert the cheek skin region to grayscale (ablation)ResNet-18 · In-domain StyleGAN vs. CelebA-HQaccuracy: 99.93% -> 99.76%No clear effect
Smooth small skin textures with an L0 filter (ablation)ResNet-18 · In-domain StyleGAN vs. CelebA-HQaccuracy: 99.93% -> 78.64%Hurt
Add Gram Blocks to the StyleGAN discriminatorGram-Net fake-face detector · StyleGAN with Gram-Block discriminator vs. CelebA-HQaccuracy: 80.55 ± 6.37 -> 93.35 ± 2.25Improved

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