Learning to hallucinate face images via component generation and enhancement

Author

Yibing SONG
Jiawei ZHANG
Shengfeng HE, Singapore Management UniversityFollow
Linchao BAO
Qingxiong YANG

Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2017

Abstract

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.

Keywords

Artificial intelligence, Tunneling (excavation)

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Information Systems and Management; Intelligent Systems and Optimization

Publication

Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI)

ISBN

9780999241103

Identifier

10.24963/ijcai.2017/633

Publisher

International Joint Conferences on Artificial Intelligence Organization

City or Country

Australia

Citation

SONG, Yibing; ZHANG, Jiawei; HE, Shengfeng; BAO, Linchao; and YANG, Qingxiong. Learning to hallucinate face images via component generation and enhancement. (2017). Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI).
Available at: https://ink.library.smu.edu.sg/sis_research/8429

Copyright Owner and License

Authors

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.