Deep Cascaded Bi-Network for Face Hallucination

 

Shizhan Zhu¹, Sifei Liu², Chen Change Loy^1,3, Xiaoou Tang^1,3

¹Department of Information Engineering, The Chinese University of Hong Kong

²University of California, Merced

³Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

 

Abstract

 

We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial configuration (e.g. facial landmarks localization or dense correspondence field), we alternatingly optimize two complementary tasks, namely face hallucination and dense correspondence field estimation, in a unified framework. In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details. Extensive experiments demonstrate that such formulation allows exceptional hallucination quality on in-the-wild low-res faces with significant pose and illumination variations.

 

 

Code Release

The code is available on the github page. Please refer to that page for details.

 

Reference

Shizhan Zhu, Sifei Liu, Chen Change Loy, Xiaoou Tang. Deep Cascaded Bi-Network for Face Hallucinationg, in Proceedings of European Conference on Computer Vision (ECCV), 2016.