Multi-View Normalization For Face Recognition

Unlike the majority of face normalization that focuses on single-view frontalization, we propose the Multi-View Normalization (MVN) framework to normalize an arbitrary face to multiple desired poses with balanced illumination and neutral expression. Taking the advantages of generative and adversarial learning, the proposed MVN transforms a face into a set of multi-view faces with facial identity well preserved, offering a better representation to handle face recognition. The MVN is designed to learn the transformation from a source set to seven target sets. The source set contains faces collected in the wild with arbitrary poses, lighting conditions and expressions. The seven target sets include seven poses from 0?ø-90?ø in yaw with 15?ø interval with balanced illumination and neutral expression. The MVN framework is composed of one face encoder, seven pose-specific generators and seven sets of discriminators. The encoder is made of a state-of-the-art face recognition network, which is not updated during training and acts as a facial feature extractor. The generators are trained to transform the source set to the seven target sets. The discriminators are trained to not only ensure the photo-realistic quality of the generated faces, but also force the poses of the generated faces to the desired poses. Experiments on several benchmark datasets demonstrate that the proposed MVN delivers a superior performance for face recognition.