AI Paper Atlas

Research map / Image generation / Editing and style transfer

Machine Pareidolia: Protecting Facial Image with Emotional Editing

Binh M. Le, Simon S. Woo

AAAI 2026 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 1 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 gradient projection between identity and emotion losses (ablation)MAP · IR152, CelebA-HQ identity 1PSR (FAR@1e-2): 71.2 -> 80.3Improved
add gradient projection (ablation)MAP · IR152, CelebA-HQ identity 1FID: 24.5 -> 21.5Improved
add EMA gradient estimate (ablation)MAP · IR152, CelebA-HQ identity 1PSR (FAR@1e-2): 76.5 -> 80.3Improved
add EMA gradient estimate (ablation)MAP · IR152, CelebA-HQ identity 1FID: 22.5 -> 21.5Improved
add Laplacian smoothness loss (ablation)MAP · IR152, CelebA-HQ identity 1PSR (FAR@1e-2): 78.8 -> 80.3Improved
add Laplacian smoothness loss (ablation)MAP · IR152, CelebA-HQ identity 1FID: 23.6 -> 21.5Improved
add emotion editing (ablation)MAP · IR152, CelebA-HQ identity 1PSR (FAR@1e-2): 85.0 -> 80.3Hurt
add emotion editing (ablation)MAP · IR152, CelebA-HQ identity 1FID: 24.1 -> 21.5Improved
set score matching weight gamma_d to 0 (remove score matching) (ablation)MAP · CelebA-HQ PSR vs FID trade-offPSR/FID trade-offHurt
replace DiffAM makeup baseline with MAP emotion editingface protection · CelebA-HQ and LADN averagePSR (FAR@1e-2): 77.88 -> 88.48Improved
use MAP instead of Adv-CPG for identificationface identification · CelebA-HQ IRSE50Rank-1 PSR: 24.4 -> 57.9Improved
use MAP instead of DiffAMface protection · Image quality averageFID: 26.10 -> 24.21Improved

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