AI Paper Atlas

Research map / Image generation / GANs

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

Shengju Qian, Kwan-Yee Lin, Wayne Wu, Yangxiaokang Liu, Quan Wang, Fumin Shen, Chen Qian, Ran He

ICCV 2019 · Image generation › GANs · approach: GAN-based image manipulation · 71 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 KL divergence loss term (ablation)AF-VAE · CelebAFID: 56.275 -> 36.820Improved
add KL divergence loss term (ablation)AF-VAE · CelebAInception Score: 1.863 -> 2.152Improved
add additive Gaussian mixture (focal) prior (ablation)AF-VAE · CelebAFID: 62.657 -> 36.820Improved
add additive Gaussian mixture (focal) prior (ablation)AF-VAE · CelebAInception Score: 1.792 -> 2.152Improved
add sub-pixel convolution (pixel shuffle) upsampling (ablation)AF-VAE · CelebAFID: 71.309 -> 36.820Improved
add sub-pixel convolution (pixel shuffle) upsampling (ablation)AF-VAE · CelebAInception Score: 1.065 -> 2.152Improved
add weight normalization in encoder and decoder (ablation)AF-VAE · CelebAFID: 65.309 -> 36.820Improved
add weight normalization in encoder and decoder (ablation)AF-VAE · CelebAInception Score: 1.365 -> 2.152Improved
use AF-VAE instead of GANimationAF-VAE · Face expression synthesis comparisonFID: 34.360 -> 25.069Improved
use AF-VAE instead of GANimationAF-VAE · Face expression synthesis comparisonInception Score: 1.112 -> 1.237Improved
use AF-VAE instead of GANimationAF-VAE · AMT realism studyFool Rate (%): 7.0% -> 36.4%Improved
replace deconvolution with sub-pixel convolution (ablation)AF-VAE · reconstruction entropyimage entropy: 7.6405 -> 7.6794No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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