Super-Identity Convolutional Neural Network for Face Hallucination

	Super-Identity Convolutional Neural Network for Face Hallucination
	Kaipeng Zhang; Zhanpeng Zhang; Chia-Wen Cheng; Winston H. Hsu; Yu Qiao; Wei Liu; Tong Zhang
	2018
会议日期	2018
英文摘要	Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heav- ily relies on identity information. However, previous face hallucination approaches largely ignore facial identity recovery. This paper proposes Super-Identity Convolutional Neural Network (SICNN) to recover iden- tity information for generating faces closed to the real identity. Specif- ically, we define a super-identity loss to measure the identity difference between a hallucinated face and its corresponding high-resolution face within the hypersphere identity metric space. However, directly using this loss will lead to a Dynamic Domain Divergence problem, which is caused by the large margin between the high-resolution domain and the hallucination domain. To overcome this challenge, we present a domain- integrated training approach by constructing a robust identity metric for faces from these two domains. Extensive experimental evaluations demonstrate that the proposed SICNN achieves superior visual quality over the state-of-the-art methods on a challenging task to super-resolve 12×14 faces with an 8× upscaling factor. In addition, SICNN significant- ly improves the recognizability of ultra-low-resolution faces.
URL标识	查看原文
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/13690]
专题	深圳先进技术研究院_集成所
推荐引用方式 GB/T 7714	Kaipeng Zhang,Zhanpeng Zhang,Chia-Wen Cheng,et al. Super-Identity Convolutional Neural Network for Face Hallucination[C]. 见:. 2018.