Attentive ExFeat based deep generative adversarial network for noise robust face super-resolution.

• A deep learning-based method is proposed for noise robust face super-resolution. • The proposed work introduces the ExFAU to suppress the noise from the SR process. • The multi-scale filters are used to learn the micro and high-level features. • A loss function is designed to preserve the identity and landmark in the face images. • Experimental results reveal the superiority of the proposed method over the state-of-the-art works. A new noise robust face super-resolution model using an attentive ExFeat-based generative adversarial network is proposed in this paper. The proposed model introduces the Exigent Feature Attention Unit (ExFAU) which consists of an Exigent Feature (ExFeat) block with a spatial attention unit to enhance the visual quality of the generated face images. The ExFAU block assists the model in reducing the noise and extracting the micro and high-level facial features. Further, the ExFeat block is followed by a spatial attention unit to focus on specific facial features. This allows us to give more attention to key face attributes related features and less to the remaining features. The proposed model repeats the ExFAU block to focus on different facial components and enhance them to improve the overall quality of the resultant face images. Experimental outcomes exhibit that the proposed model gains state-of-the-art performance on the standard datasets, namely CelebAHQ, Helen, and LFW face. [ABSTRACT FROM AUTHOR]