AI Paper Atlas

Research map / Image generation / Editing and style transfer

FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing

Fengjian Xue, Xuecheng Wu, Heli Sun, Yunyun Shi, Shi Chen, Liangyu Fu, Jinheng Xie, Dingkang Yang, Hao Wang, Junxiao Xue, Liang He

ECCV 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 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
fine-tune on the 20k+ FED training setFLUX-Kontext-Dev · FED-Bench (dense instructions)FED-Score: .243 -> .332Improved
fine-tune on the 20k+ FED training setFLUX-Kontext-Dev · FED-Bench (simple instructions)FED-Score: .120 -> .325Improved
add Relative Expression Gain dimension to FED-Score (ablation)FED-Score · Human alignment, overallagreement with human: 0.7577 -> 0.7700Improved
add Fidelity dimension (ablation)FED-Score · Human alignment, overallagreement with human: 0.7379 -> 0.7700Improved
add Alignment dimension (ablation)FED-Score · Human alignment, overallagreement with human: 0.7279 -> 0.7700Improved
add MLLM-based model metrics (ablation)FED-Score · Human alignment, overallagreement with human: 0.7202 -> 0.7700Improved
add rule-based metrics (ablation)FED-Score · Human alignment, overallagreement with human: 0.7422 -> 0.7700Improved
use LPIPS ratio to GT instead of raw LPIPS to GT for expression magnitudeREG metric · Human alignment, REGagreement with human: 0.7045 -> 0.7386Improved
use FED-Score instead of best single baseline CLIP-I_GToverall evaluation metric · Human alignment, overallagreement with human: 0.6850 -> 0.7700Improved
use ground-truth-referenced variants of metricsDINO, LPIPS, CLIP-I · Human alignment, overallagreement with human: 0.5816 -> 0.6216 (DINO)Improved
regroup 7 expressions into 3 polarities (coarse-grained recognition)Gemini-2.5-Pro · expression recognitionaccuracy: 64.93% -> 81.23%Improved
use 5-model voting ensemble instead of 3-model (ablation)MLLM ensemble · expression recognition (fine)best accuracy: 66.13 -> 66.67Improved

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