Type of Publication

Conference Papers

Date:

7 /

2025

Status

Published

DOI:

10.1007/978-3-031-99565-1_19

Pseudo-MOS Learning: A Full-to-No-Reference FIQA Framework

Featured in:

12th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 2025)

Authors:

André Neto; Nuno Gonçalves

Abstract
A persistent gap remains between standard Image Quality Assessment (IQA) metrics and human perceptual judgments, typically quantified via Mean Opinion Scores (MOS). This poses a key challenge in applications where perceived quality impacts performance, such as facial recognition. We introduce a new no-reference Face Image Quality Assessment (FIQA) metric, developed within a Full-to-No-Reference learning framework. The process begins with a full-reference fusion model trained to regress classical IQA scores against human MOS on a labeled subset. This model is used to generate pseudo-MOS scores for the full dataset. These labels then supervise a no-reference deep regressor based on ResNet-18 features, producing a perceptually aligned metric that estimates quality directly from distorted facial images. We tested our approach in the context of steganographically degraded facial images, showing its effectiveness in scenarios involving subtle distortions and limited human annotations.
Citation
André Neto and Nuno Gonçalves. (2026). Pseudo-MOS Learning: A Full-to-No-Reference FIQA Framework. In: Nuno Gonçalves, Hélder P. Oliveira, Joan Andreu Sánchez. (eds) Pattern Recognition and Image Analysis. IbPRIA 2025. Lecture Notes in Computer Science, vol 15937. Springer, Cham. https://doi.org/10.1007/978-3-031-99565-1_19

Related Content

Researcher Coordinator, VIS TEAM Leader
Master Student
News: Dissemination
Four papers presented @ IbPRIA 2025
July 4, 2025
Project In progress
ACHILLES
Inspired by the Olympic motto “Citius, Altius, Fortius...
No tagged content to show

RECENT PUBLICATIONS

Biometrics under attack: On provenance, trust and threat robustness

Authors: Guilherme Schardong; Tiago Novello; Luiz Silva; Nuno Gonçalves
Featured in: 39th Conference on Graphics, Patterns and Images

STATISTICAL ANALYSIS OF RETINAL ARTERIAL NETWORKS: Graph-Based Radiomics Framework

Authors: Ofélio Jorreia; Nuno Gonçalves, Rui Cortesão
Featured in: IEEE Access

MorphGuard: Morph Specific Margin Loss for Enhancing Robustness to Face Morphing Attacks

Authors: Iurii Medvedev; Ajnas Muhammed; Nuno Gonçalves
Featured in: 11th International Conference on Computer Vision & Image Processing (CVIP 2026)

suggested news

VIS Team will host a session presenting the...
Paper presented at NeurIPS 2025
VIS Team has presented workshop at the 12th...

RECENT PROJECTS

FACING2 – Face Image Understanding
VISUAL-ID – Unique Visual Identities in Graphics, Images and Faces
UniqueMark

Institute of Systems and Robotics Department of Electrical and Computers Engineering University of Coimbra