JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution

Abstract

With the growing importance of preventing the COVID-19 virus, face images obtained in most video surveillance scenarios are low resolution with mask simultaneously. However, most of the previous face super-resolution solutions can not handle both tasks in one model. In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task. Given a low-quality face image with the mask as input, the role of the generator composed of a denoising module and super-resolution module is to acquire a high-quality high-resolution face image. The discriminator utilizes some carefully designed loss functions to ensure the quality of the recovered face images. Moreover, we incorporate the identity information and attention mechanism into our network for feasible correlated feature expression and informative feature learning. By jointly performing denoising and face super-resolution, the two tasks can complement each other and attain promising performance. Extensive qualitative and quantitative results show the superiority of our proposed JDSR-GAN over some comparable methods which perform the previous two tasks separately.

IEEE Transactions on Multimedia, 8 pages, 7 figures

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Learning Spatial Attention for Face Super-Resolution
• CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution
• Robust Face Alignment by Multi-order High-precision Hourglass Network
• Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition
• Face Hallucination via Split-Attention in Split-Attention Network