collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion

Tahar Chettaoui, Eduarda Caldeira, Guray Ozgur +3

Advancing face morphing attack techniques is crucial to anticipate evolving threats and develop robust defensive mechanisms for identity verification systems. This work introduces…

cs.CV2026

On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection

Eduarda Caldeira, Guray Ozgur, Fadi Boutros +1

This study investigates the impact of face image background correction through segmentation on face recognition and morphing attack detection performance in realistic, unconstraine…

cs.CV2026

EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment

Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira +4

Face Image Quality Assessment is crucial for reliable face recognition systems, yet existing Vision Transformer-based approaches rely exclusively on final-layer representations, ig…

cs.CV2026

ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers

Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira +5

Face Image Quality Assessment (FIQA) aims to assess the recognition utility of face samples and is essential for reliable face recognition (FR) systems. Existing approaches require…

cs.CV2026

ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers

Guray Ozgur, Eduarda Caldeira, Tahar Chettaoui +4

Face Image Quality Assessment (FIQA) is essential for reliable face recognition systems. Current approaches primarily exploit only final-layer representations, while training-free…

cs.CV2025

MADation: Face Morphing Attack Detection with Foundation Models

Eduarda Caldeira, Guray Ozgur, Tahar Chettaoui +5

Despite the considerable performance improvements of face recognition algorithms in recent years, the same scientific advances responsible for this progress can also be used to cre…