AI Paper Atlas

Research map / Image generation / Editing and style transfer

Identity-Preserving Face Recovery from Stylized Portraits

Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz

IJCV 2019 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 20 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 discriminative loss to pixel-wise loss (ablation)IFRP · Seen styles (CelebA test)FSIM: 0.72 -> 0.75Improved
add discriminative loss to pixel-wise loss (ablation)IFRP · Stylized faces, unseen styles (CelebA test)SSIM: 0.54 -> 0.58Improved
add identity-preserving loss to pixel and discriminative losses (ablation)IFRP · Stylized faces, unseen styles (CelebA test)SSIM: 0.58 -> 0.68Improved
add identity-preserving loss to pixel and discriminative losses (ablation)IFRP · Seen styles (CelebA test)SSIM: 0.62 -> 0.72Improved
use residual blocks on top-2-layer skip connections instead of a standard autoencoder (ablation)IFRP · Seen styles (CelebA test)SSIM: 0.65 -> 0.72Improved
use residual top-2 skip connections instead of U-net skip connections (ablation)IFRP · Stylized faces, unseen styles (CelebA test)SSIM: 0.61 -> 0.68Improved
add STN layers (ablation)IFRP (3 training styles) · training convergenceepochs to converge: 165 -> 143Improved
increase number of training styles from 1 to 3IFRP · Stylized faces, unseen styles (CelebA test)SSIM: 0.54 -> 0.68Improved
increase number of training styles from 3 to 5IFRP · Stylized faces, unseen styles (CelebA test)SSIM: 0.68 -> 0.69No clear effect
increase training styles from 1 to 5 raises training time per epochIFRP · training timetime per epoch: 1:49' -> 9:47'Hurt
use fewer rotation augmentations (5 angles instead of 11) with STNs (ablation)IFRP · augmentation studySSIM: 0.66 -> 0.65No clear effect

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