GraFIQs: Face Image Quality Assessment Using Gradient Magnitudes

Jan Niklas Kolf, Naser Damer, Fadi Boutros; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 1490-1499

Face Image Quality Assessment (FIQA) estimates the utility of face images for automated face recognition (FR) systems. We propose in this work a novel approach to assess the quality of face images based on inspecting the required changes in the pre-trained FR model weights to minimize differences between testing samples and the distribution of the FR training dataset. To achieve that we propose quantifying the discrepancy in Batch Normalization statistics (BNS) including mean and variance between those recorded during FR training and those obtained by processing testing samples through the pretrained FR model. We then generate gradient magnitudes of pretrained FR weights by backpropagating the BNS through the pretrained model. The cumulative absolute sum of these gradient magnitudes serves as the FIQ for our approach. Through comprehensive experimentation we demonstrate the effectiveness of our training-free and quality labeling-free approach achieving competitive performance to recent state-of-theart FIQA approaches without relying on quality labeling the need to train regression networks specialized architectures or designing and optimizing specific loss functions.