Abstract
Face image super-resolution refers to recovering a high-resolution face image from a low-resolution one. In recent years, due to the breakthrough progress of deep representation learning for super-resolution, the study of face super-resolution has become one of the hot topics in the field of super-resolution. However, the performance of these deep learning-based approaches highly relies on the scale of training samples and is limited in efficiency in real-time applications. To address these issues, in this work, we introduce a novel method based on the parallel imaging theory and OpenVINO. In particular, inspired by the methodology of learning-by-synthesis in parallel imaging, we propose to learn from the combination of virtual and real face images. In addition, we introduce a center loss function borrowed from the deep model to enhance the robustness of our model and propose to apply OpenVINO to speed up the inference. To the best of our knowledge, it is the first time to tackle the problem of face super-resolution based on parallel imaging methodology and OpenVINO. Extensive experimental results and comparisons on the publicly available LFW, WebCaricature, and FERET datasets demonstrate the effectiveness and efficiency of the proposed method.
Highlights
Image super-resolution (SR) is a classical issue in the engineering field of image processing technology and computer vision [1]. e face super-resolution problem is one of the important branches of the super-resolution problem
Dong et al [16] validated that CNN can achieve an end-to-end learning effectively from low-resolution images to high-resolution images and proposed the single-image reconstruction convolutional neural networks (SRCNN), and in 2016, Dong et al [17] proposed a method (FSRCNN) based on compact hourglass-shaped CNN structure to reconstruct HR image by introducing a deconvolution layer
There are three contributions in this paper: (1) We propose a face super-resolution method based on parallel imaging theory with high robustness and efficiency
Summary
Received 11 December 2020; Revised 26 January 2021; Accepted 29 January 2021; Published 15 February 2021. The performance of these deep learning-based approaches highly relies on the scale of training samples and is limited in efficiency in real-time applications. To address these issues, in this work, we introduce a novel method based on the parallel imaging theory and OpenVINO. Inspired by the methodology of learning-by-synthesis in parallel imaging, we propose to learn from the combination of virtual and real face images. To the best of our knowledge, it is the first time to tackle the problem of face superresolution based on parallel imaging methodology and OpenVINO. Extensive experimental results and comparisons on the publicly available LFW, WebCaricature, and FERET datasets demonstrate the effectiveness and efficiency of the proposed method
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have