Abstract
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-FIQA, a training-free 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, IJB-C), 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.
Abstract (translated)
面部图像质量评估（FIQA）对于可靠的脸部识别系统至关重要。目前的方法主要利用最终层的表示，而无需训练的方法则需要多次前向传递或反向传播。我们提出了ViTNT-FIQA，这是一种无需训练的方法，它通过测量中间Vision Transformer (ViT) 块中补丁嵌入演化的稳定性来评估图像质量。我们展示了高质量的脸部图像在整个块中的特征细化路径表现出稳定的状态，而质量较差的图像则显示出不规则的变化。我们的方法计算了连续变换器块之间的L2标准化补丁嵌入的欧几里得距离，并将这些距离汇总为图像级别的质量分数。我们在一个合成数据集上验证了这种相关性，该数据集中存在受控降级水平的质量标记。 与现有的无需训练的方法不同，ViTNT-FIQA仅需要单次前向传递，不需要反向传播或架构修改。通过在八个基准测试（LFW、AgeDB-30、CFP-FP、CALFW、Adience、CPLFW、XQLFW、IJB-C）上的广泛评估，我们展示了ViTNT-FIQA能够实现与现有最佳方法相当的性能，同时保持计算效率，并且可以立即应用于任何基于预训练Vision Transformer的脸部识别模型。
URL
https://arxiv.org/abs/2601.05741
