Research · Guray Ozgur

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

Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf, Marco Huber, Andrea Atzori, Naser Damer, Fadi Boutros

IEEE International Conference on Automatic Face and Gesture Recognition, 2026

Uses attention maps as a quality signal, which also indicates which regions of a face led to a low score.

arXiv Code Poster

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

Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira, Jan Niklas Kolf, Andrea Atzori, Fadi Boutros, Naser Damer

IEEE International Conference on Automatic Face and Gesture Recognition, 2026

Estimates face image quality from the intermediate layers of a vision transformer, so a full forward pass is not required.

arXiv Code Poster

EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment

Guray Ozgur, Mustafa Efe Tamyapar, Naser Damer, Fadi Boutros

European Conference on Computer Vision Workshops, 2026

Aligns face embeddings with language so that a recognition decision can be described in words.

Code Poster

Figure from Tomatoes, Potatoes, and Onions

Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection

Guray Ozgur, Fadi Boutros, Naser Damer

ACM International Conference on Multimedia Workshops, 2026

Trains presentation attack detection on images of vegetables rather than faces, and looks at what the models were relying on.

Code

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

Guray Ozgur, Eduarda Caldeira, Tahar Chettaoui, Jan Niklas Kolf, Marco Huber, Naser Damer, Fadi Boutros

IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2026

Estimates face image quality from a pretrained vision transformer with no training and no quality labels.

arXiv Code

IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data

Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira, Arturas Nakvosas, Hatef Otroshi Shahreza, Sebastien Marcel, Rishabh Shukla, Aditya Takkar, Rushil Khullar, Lalak Yadav, Gourav Gupta, Anant Gupta, Shiqi Yu, Vitomir Struc, Naser Damer, Fadi Boutros

IEEE International Joint Conference on Biometrics, 2026

Report of a competition on adapting foundation models for face recognition using synthetic training data.

arXiv Code

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

Eduarda Caldeira, Guray Ozgur, Fadi Boutros, Naser Damer

IEEE International Conference on Automatic Face and Gesture Recognition, 2026

Measures how removing the image background changes face recognition and morphing attack detection.

arXiv Code

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

Tahar Chettaoui, Eduarda Caldeira, Guray Ozgur, Raghavendra Ramachandra, Fadi Boutros, Naser Damer

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2026

Generates face morphs with a diffusion model that uses two streams and cross attention.

arXiv Code

Vision Transformers for Face Recognition Need More Registers

Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira, Naser Damer, Fadi Boutros

IEEE International Conference on Automatic Face and Gesture Recognition, 2026

Measures what register tokens do inside vision transformers trained for face recognition.

arXiv Code

PreFIQs: Face Image Quality Is What Survives Pruning

Jan Niklas Kolf, Guray Ozgur, Andrea Atzori, Ziga Babnik, Vitomir Struc, Naser Damer, Fadi Boutros

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2026

Shows that what survives pruning in a face recognition model carries a usable quality signal.

arXiv Code

ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation

Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira, Naser Damer, Fadi Boutros

IEEE International Conference on Automatic Face and Gesture Recognition, 2026

Adds early exits to a face recognition transformer and adapts it with synthetic data.

arXiv

FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection

Guray Ozgur, Eduarda Caldeira, Tahar Chettaoui, Fadi Boutros, Raghavendra Ramachandra, Naser Damer

IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2025

Adapts foundation models to presentation attack detection and reports how they behave with limited training data and across domains.

PDF arXiv Code

MADation: Face Morphing Attack Detection with Foundation Models

Eduarda Caldeira, Guray Ozgur, Tahar Chettaoui, Marija Ivanovska, Peter Peer, Fadi Boutros, Vitomir Struc, Naser Damer

IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2025

Adapts foundation models to morphing attack detection.

PDF arXiv Code

A Comprehensive Literature Review on Voltage Reference Circuits: Analysis and Comparison of State-of-the-Art Designs

Guray Ozgur

engrXiv, 2020

Compares thirty voltage reference circuit designs published during the 2010s.

Code