VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results

TL;DR

The VQualA 2025 Challenge on Face Image Quality Assessment aimed to develop efficient models for predicting face image quality under real-world degradations, fostering advancements in practical FIQA methods.

Contribution

This paper presents the organization and results of the VQualA 2025 Challenge, highlighting new lightweight models for face image quality assessment under realistic conditions.

Findings

127 participants contributed

1519 submissions evaluated

Models achieved high correlation with human quality scores

Abstract

Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.