AI Paper Atlas

Research map / Image generation / Editing and style transfer

SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters

Evangelos Ververas, Stefanos P. Zafeiriou

IJCV 2020 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 26 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
replace WGP-GP adversarial loss with relativistic discriminator (RaD) (ablation)SliderGAN · 4DFAB expression transferIED: 7.932-03 -> 6.84e-03Improved
replace WGP-GP adversarial loss with relativistic discriminator (RaD) (ablation)SliderGAN · LRW expression and speech synthesisIED: 1.14e-02 -> 9.35e-03Improved
replace WGP-GP adversarial loss with relativistic discriminator (RaD) (ablation)SliderGAN · EmotionNet expression recognitionaverage accuracy: 0.614 -> 0.636Improved
use 3D blendshape parameters instead of action unit activationsSliderGAN vs GANimation · 4DFAB expression transferIED: 1.04e-02 -> 6.84e-03Improved
use blendshape parameters instead of action unitsSliderGAN vs GANimation · LRW expression and speech synthesisIED: 3.07e-02 -> 9.35e-03Improved
use blendshape parameters instead of action unitsSliderGAN vs GANimation · EmotionNet expression recognitionaverage accuracy: 0.579 -> 0.636Improved
use blendshape parameters instead of action units (discriminator regression)SliderGAN vs GANimation · EmotionNet parameter regression vs fittingrelative parameter error: 0.427 -> 0.131Improved
use blendshape parameters instead of action units (discriminator regression)SliderGAN vs GANimation · EmotionNet parameter consistency after translationrelative parameter error: 0.513 -> 0.258Improved
add identity loss L_id to the generator loss (ablation)SliderGAN · face generation (qualitative)image realism and identityImproved
add semi-supervised generation loss L_gen on paired data (ablation)SliderGAN · face generation (qualitative)image qualityImproved

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