Multi-View Texture Learning for Face Super-Resolution

Abstract

In recent years, single face image super-resolution (SR) using deep neural networks have been well developed. However, most of the face images captured by the camera in a real scene are from different views of the same person, and the existing traditional multi-frame image SR requires alignment between images. Due to multi-view face images contain texture information from different views, which can be used as effective prior information, how to use this prior information from multi-views to reconstruct frontal face images is challenging. In order to effectively solve the above problems, we propose a novel face SR network based on multi-view face images, which focus on obtaining more texture information from multi-view face images to help the reconstruction of frontal face images. And in this network, we also propose a texture attention mechanism to transfer high-precision texture compensation information to the frontal face image to obtain better visual effects. We conduct subjective and objective evaluations, and the experimental results show the great potential of using multi-view face images SR. The comparison with other state-of-the-art deep learning SR methods proves that the proposed method has excellent performance.

3D face recognition algorithm based on deep Laplacian pyramid under the normalization of epidemic control

“…Curvilinear method Drira et al. [25] used the radial curve based on the nose tip to represent the whole face surface. In this method, the nose tip is first located, and then the face surface is segmented by a plane passing through the nose tip at every certain Angle.…”