Deep Cascaded Bi-Network for Face Hallucination
文献类型：会议论文
| 作者 | Shizhan Zhu; Sifei Liu; Chen Change Loy; Xiaoou Tang |
| 出版日期 | 2016 |
| 会议名称 | ECCV2016 |
| 会议地点 | 荷兰阿姆斯特丹 |
| 英文摘要 | We present a novel framework for hallucinating faces of un- constrained poses and with very low resolution (face size as small as 5pxIOD1). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial con guration (e.g. facial landmarks localization or dense correspondence eld), we alternatingly optimize two comple- mentary tasks, namely face hallucination and dense correspondence eld estimation, in a uni ed framework. In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover di erent levels of texture details. Extensive experiments demon- strate that such formulation allows exceptional hallucination quality on in-the-wild low-res faces with signi cant pose and illumination variations. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/10025]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2016 |
| 推荐引用方式 GB/T 7714 | Shizhan Zhu,Sifei Liu,Chen Change Loy,et al. Deep Cascaded Bi-Network for Face Hallucination[C]. 见:ECCV2016. 荷兰阿姆斯特丹. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。