Publikationen

Autor	Ozgur, Guray; Loureiro Caldeira, Maria Eduarda; Chettaoui, Tahar; Kolf, Jan Niklas; Huber, Marco; Damer, Naser; Boutros, Fadi
Datum	2026
Art	Paper
Abstrakt	Face Image Quality Assessment (FIQA) is essential for reliable face recognition systems. Current approaches primarily exploit only final-layer representations, while training-free methods require multiple forward passes or backpropagation. We propose ViTNT-FIQA1, a trainingfree approach that measures the stability of patch embedding evolution across intermediate Vision Transformer (ViT) blocks. We demonstrate that high-quality face images exhibit stable feature refinement trajectories across blocks, while degraded images show erratic transformations. Our method computes Euclidean distances between L2-normalized patch embeddings from consecutive transformer blocks and aggregates them into image-level quality scores. We empirically validate this correlation on a quality-labeled synthetic dataset with controlled degradation levels. Unlike existing training-free approaches, ViTNT-FIQA requires only a single forward pass without backpropagation or architectural modifications. Through extensive evaluation on eight benchmarks (LFW, AgeDB- 30, CFP-FP, CALFW, Adience, CPLFW, XQLFW, IJBC), we show that ViTNT-FIQA achieves competitive performance with state-of-the-art methods while maintaining computational efficiency and immediate applicability to any pre-trained ViT-based face recognition model.
Konferenz	Winter Conference on Applications of Computer Vision 2026
Projekt	Next Generation Biometric Systems
Url	https://publica.fraunhofer.de/handle/publica/511495