Guided Cascaded Super-Resolution Network for Face Image

Abstract

The image super-resolution algorithm can overcome the imaging system's hardware limitation and obtain higher resolution and clearer images. Existing super-resolution methods based on convolutional neural networks(CNN) can learn the mapping relationship between high-resolution(HR) and low-resolution(LR) images. However, when the reconstruction target is a face image, the reconstruction results often have problems that the face area is too smooth and lacks details. We propose a guided cascaded face super-resolution network, called guided cascaded super-resolution network (GCFSRnet). GCFSRnet takes the LR image and a high-quality guided image as inputs, and it consists of a pose deformation module and a super-resolution network. Firstly, the pose deformation module converts the guide image's posture into the same as the low-resolution face image based on 3D fitting and 3D morphable model (3DMM). Then, the LR image and the deformed guide image are used as input of the super-resolution network. The super-resolution networks are formed by a cascade of two layers of networks, which extract different features. During the reconstruction process, the guide image can provide real facial details and help generate subtle facial textures. The cascade structure of a super-resolution network can gradually extract features and restore different levels of image details. The experimental results on the CASIA Web Face and CelebA datasets show that the proposed method can generate facial images with clear outlines and rich details, which are superior to other state-of-the-art methods such as SRResNet, SRGAN, VDSR, DBPN, etc.

Deep Learning-based Face Super-Resolution: A Survey

“…At first, a high-quality face image which shares the same identity of LR serves as R, such as guided face restoration network (GFRNet) [97], guidance warper adversarial-loss, identity-loss network (GWAInet) [34] and guided cascaded super-resolution network (GCFSRNet) [17]. Since R and LR may have different poses and expressions, which may hinder the recovery of face images, single-face guided methods tend to perform the alignment between R and After alignment, both LR and aligned R (we name it w ) are fed into a reconstruction network to repair the SR.…”