Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network
This addresses the problem of accurate face identification from very low-resolution images, which is incremental as it builds on existing super-resolution and recognition methods.
The paper tackles face verification on very low-resolution images by proposing an identity-preserving deep face super-resolution network, and results show it outperforms conventional super-resolution methods in verification tasks across multiple datasets.
Face super-resolution methods usually aim at producing visually appealing results rather than preserving distinctive features for further face identification. In this work, we propose a deep learning method for face verification on very low-resolution face images that involves identity-preserving face super-resolution. Our framework includes a super-resolution network and a feature extraction network. We train a VGG-based deep face recognition network (Parkhi et al. 2015) to be used as feature extractor. Our super-resolution network is trained to minimize the feature distance between the high resolution ground truth image and the super-resolved image, where features are extracted using our pre-trained feature extraction network. We carry out experiments on FRGC, Multi-PIE, LFW-a, and MegaFace datasets to evaluate our method in controlled and uncontrolled settings. The results show that the presented method outperforms conventional super-resolution methods in low-resolution face verification.