Authors:
Jichun Li; Bahetiyaer Bare; Shili Zhou; Bo Yan; Ke Li
Publication:
This paper is included in the Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), July 5-9, 2021.
Abstract:
In this paper, we present a novel organ-branched CNN method for face super-resolution, named OBC-FSR. It is the first work focusing on facial-part-specific face SR, which consists of a local (facial part) network and a global network. Specifically, local network is able to enhance the five key regions of human faces separately by Wasserstein generative adversarial networks (WGAN). Simultaneously, it can also predict the mask of five key regions respectively, namely eyes, eyebrows, mouth, nose, and other parts. Output of local network can be obtained by merging super-resolved five key regions. In order to alleviate boundary effects and distortions in the result of local network, our proposed network also includes a global network, which learns the direct mapping between LR and HR human faces. The final HR result of our FSR method is a fusion of the outputs of local and global networks. Experimental results verify the superior performance of our proposed method compared to state-of-the-art FSR methods.