Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors
It addresses the problem of recovering local details in face super-resolution for applications like surveillance or forensics, representing an incremental improvement over prior methods.
The paper tackles face super-resolution by proposing a recurrent convolutional network that progressively integrates global shape and local texture information, using landmarks and facial action units extracted from intermediate outputs, and it significantly outperforms state-of-the-art methods in image quality and facial details restoration.
The face super-resolution (FSR) task is to reconstruct high-resolution face images from low-resolution inputs. Recent works have achieved success on this task by utilizing facial priors such as facial landmarks. Most existing methods pay more attention to global shape and structure information, but less to local texture information, which makes them cannot recover local details well. In this paper, we propose a novel recurrent convolutional network based framework for face super-resolution, which progressively introduces both global shape and local texture information. We take full advantage of the intermediate outputs of the recurrent network, and landmarks information and facial action units (AUs) information are extracted in the output of the first and second steps respectively, rather than low-resolution input. Moreover, we introduced AU classification results as a novel quantitative metric for facial details restoration. Extensive experiments show that our proposed method significantly outperforms state-of-the-art FSR methods in terms of image quality and facial details restoration.