Learning to hallucinate face images via component generation and enhancement

• Main Authors: SONG, Yibing, ZHANG, Jiawei, HE, Shengfeng, BAO, Linchao, YANG, Qingxiong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Artificial intelligence; Tunneling (excavation); Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8429; https://ink.library.smu.edu.sg/context/sis_research/article/9432/viewcontent/0633.pdf
• Institution: Singapore Management University

We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods.