AI Paper Atlas

Research map / Image generation / Editing and style transfer

Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis

Rui Huang, Shu Zhang, Tianyu Li, Ran He

ICCV 2017 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 706 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 the local pathway (ablation)TP-GAN · MultiPIE Setting 2 (+-90 degrees)Rank-1 (%): 44.13 -> 64.64Improved
add the identity preserving loss (ablation)TP-GAN · MultiPIE Setting 2 (+-90 degrees)Rank-1 (%): 43.23 -> 64.64Improved
add the adversarial loss (ablation)TP-GAN · MultiPIE Setting 2 (+-90 degrees)Rank-1 (%): 62.83 -> 64.64Improved
add the symmetry loss (ablation)TP-GAN · MultiPIE Setting 2 (+-90 degrees)Rank-1 (%): 62.47 -> 64.64Improved
add the local pathway (ablation)TP-GAN · MultiPIE Setting 2 (+-60 degrees)Rank-1 (%): 80.64 -> 87.72Improved
add the identity preserving loss (ablation)TP-GAN · MultiPIE Setting 2 (+-60 degrees)Rank-1 (%): 70.99 -> 87.72Improved
add the adversarial loss (ablation)TP-GAN · MultiPIE Setting 2 (+-15 degrees)Rank-1 (%): 98.09 -> 98.68Improved
add the symmetry loss (ablation)TP-GAN · MultiPIE Setting 2 (+-15 degrees)Rank-1 (%): 98.47 -> 98.68Improved
frontalize with TP-GAN before recognition versus raw profile images with Light CNNLight CNN features · MultiPIE Setting 1 (+-90 degrees)Rank-1 (%): 9.00 -> 64.03Improved
frontalize with TP-GAN before recognitionLight CNN features · MultiPIE Setting 1 (+-15 degrees)Rank-1 (%): 99.78 -> 99.78No clear effect
frontalize with TP-GAN before recognitionLight CNN features · MultiPIE Setting 2 (+-90 degrees)Rank-1 (%): 5.51 -> 64.64Improved
use TP-GAN synthesized images instead of original profile imagesgender classifier · MultiPIE Setting 1 gender (+-45 degrees)accuracy (%): 86.22 -> 90.71Improved

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