AI Paper Atlas

Research map / Image generation / Editing and style transfer

MR-FIQA: Face Image Quality Assessment with Multi-Reference Representations from Synthetic Data Generation

Fu-Zhao Ou, Chongyi Li, Shiqi Wang, Sam Kwong

ICCV 2025 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 5 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 occlusion control via text prompts (ablation)SynFIQA generation · avg of CPLFW, Adience, TinyFacepAUC: 0.792 -> 0.781Improved
add blur/downsampling post-processing (ablation)SynFIQA generation with OC · avg of CPLFW, Adience, TinyFacepAUC: 0.781 -> 0.738Improved
add MR-FIQA quality labels in place of CR-FIQA training labels (ablation)SynFIQA · 8 test sets avgpAUC: 0.800 -> 0.730Improved
add MR-FIQA quality labels in place of CR-FIQA training labels (ablation)SynFIQA · 8 test sets avgAUC: 0.554 -> 0.520Improved
use MR-FIQA instead of CR-FIQA labels (ablation)MobileFaceNet FIQA on SynFIQA · avg of 4 test setsavg: 0.596 -> 0.572Improved
use FaceQnet instead of SDD-FIQA labels (ablation)MobileFaceNet FIQA on SynFIQA · avg of 4 test setsavg: 0.652 -> 0.643Improved
add spatial-domain score sd to recognition-domain fr (ablation)MR-FIQA · avg of CPLFW, Adience, TinyFacepAUC: 0.765 -> 0.723Improved
add vision-language score vl to recognition-domain fr (ablation)MR-FIQA · avg of CPLFW, Adience, TinyFacepAUC: 0.765 -> 0.731Improved
add vision-language score vl to fr+sd (ablation)MR-FIQA · avg of CPLFW, Adience, TinyFacepAUC: 0.723 -> 0.683Improved
use fr alone vs sd alone vs vl alone (ablation)MR-FIQA · avg of CPLFW, Adience, TinyFacepAUC: 0.765 vs 0.816 vs 0.858Mixed
train on SynFIQA instead of real CASIA-WebFace (SynFIQA++ vs CASIA)CR-FIQA IR50 · 8 test sets avgpAUC: 0.701 -> 0.730Hurt
combine SynFIQA with CASIA-WebFace (ablation)CR-FIQA IR50 · LFW, XQLFW, AgeDB, CP-LFW, CFP-FPpAUCImproved

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