Face Hallucination Based on Key Parts Enhancement
Ke Li, Bahetiyaer Bare, Bo Yan, Bailan Feng, Chunfeng Yao
Abstract
Face hallucination aims to generate a high resolution face from a low resolution one. Generic super resolution methods can not solve this problem well, because human face has a strong structure. With the rapid development of the deep learning technique, some convolutional neural networks (CNNs) models for face hallucination emerged and achieved state-of-the-art performance. In this paper, we proposed a five-branch network based on five key parts of human face. Each branch of this network aims to generate a high resolution key part. The final high resolution face is the combination of the five branches' output. In addition, we designed a gated enhance unit (GEU) and cascade it to form our network architecture. Experimental results confirm that our method can generate pleasing high resolution faces.
BibTeX
@inproceedings{icassp2018_facehallucinatio,
title = {Face Hallucination Based on Key Parts Enhancement},
author = {Ke Li and Bahetiyaer Bare and Bo Yan and Bailan Feng and Chunfeng Yao},
booktitle = {ICASSP 2018},
year = {2018}
}