Effective Face Frontalization in Unconstrained Images
This addresses the challenge of face recognition in unconstrained viewpoints for computer vision applications, though it is incremental as it builds on prior frontalization methods.
The paper tackles the problem of synthesizing frontal views from unconstrained face images by using a single 3D surface approximation instead of estimating 3D shapes per image, resulting in a straightforward method that improves face recognition and gender estimation.
"Frontalization" is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos. Recent reports have suggested that this process may substantially boost the performance of face recognition systems. This, by transforming the challenging problem of recognizing faces viewed from unconstrained viewpoints to the easier problem of recognizing faces in constrained, forward facing poses. Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image. We observe that 3D face shape estimation from unconstrained photos may be a harder problem than frontalization and can potentially introduce facial misalignments. Instead, we explore the simpler approach of using a single, unmodified, 3D surface as an approximation to the shape of all input faces. We show that this leads to a straightforward, efficient and easy to implement method for frontalization. More importantly, it produces aesthetic new frontal views and is surprisingly effective when used for face recognition and gender estimation.