AI Paper Atlas

Research map / Image generation / Editing and style transfer

IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbations

Fadi Boutros, Eduarda Caldeira, Tahar Chettaoui, Naser Damer

CVPR 2026 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 0 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
perturb identity embeddings within a cone (lb 0.6) instead of a fixed embedding (ablation)IDiff-Face (C-WF) · Face verification avg of 5 benchmarksaverage accuracy (%): 91.25 -> 93.62Improved
perturb identity embeddings within a cone (lb 0.5) instead of a fixed embedding (ablation)IDiff-Face (FFHQ) · Face verification avg of 5 benchmarksaverage accuracy (%): 86.58 -> 88.79Improved
lower the cone bound lb from 0.6 to 0.4 (ablation)IDPERTURB (C-WF) · Face verification avg of 5 benchmarksaverage accuracy (%): 93.62 -> 93.36Hurt
lower lb (wider cone) on intra-class diversity (ablation)IDPERTURB (C-WF) · Intra-class diversityD-intra (LPIPS): 0.325 -> 0.538 (lb 0.9 -> 0.4)Improved
lower lb (wider cone) on identity consistency (ablation)IDPERTURB (C-WF) · Intra-class consistencyC-intra: 0.998 -> 0.790 (lb 0.9 -> 0.4)Hurt
increase CFG scale from 1 to 5 (ablation)IDPERTURB (C-WF, lb 0.6) · Face verification avg of 5 benchmarksaverage accuracy (%): 93.62 -> 92.42Hurt
use CFG scale 1-2 instead of 0 (no guidance) (ablation)IDPERTURB (C-WF, lb 0.6) · Face verification avg of 5 benchmarksaverage accuracy (%): 92.97 -> 93.62Improved
add IDPERTURB to Arc2Face generationArc2Face · Face verification avg of 5 benchmarksaverage accuracy (%): 89.71 -> 91.32Improved
add IDPERTURB to Arc2Face generationArc2Face · LFWaccuracy (%): 98.90 -> 98.93No clear effect
scale IDPERTURB data from 0.5M to 1.0M imagesIDPERTURB (C-WF) · Face verification avg of 5 benchmarksaverage accuracy (%): 93.62 -> 94.48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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