Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
2-2020
Abstract
Photorealistic multi-view face synthesis from a single image is an important but challenging problem. Existing methods mainly learn a texture mapping model from the source face to the target face. However, they fail to consider the internal deformation caused by the change of poses, leading to the unsatisfactory synthesized results for large pose variations. In this paper, we propose a Gated Deformable Face Synthesis Network to model the deformation of faces that aids the synthesis of the target face image. Specifically, we propose a dual network that consists of two modules. The first module estimates the deformation of two views in the form of convolution offsets according to the input and target poses. The second one, on the other hand, leverages the predicted deformation offsets to create the target face image. In this way, pose changes are explicitly modeled in the face generator to cope with geometric transformation, by adaptively focusing on pertinent regions of the source image. To compensate offset estimation errors, we introduce a soft-gating mechanism that enables adaptive fusion between deformable features and primitive features. Extensive experimental results on five widely-used benchmarks show that our approach performs favorably against the state-of-the-arts on multi-view face synthesis, especially for large pose changes.
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Information Systems and Management
Publication
Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, 2020 February 7-12
Volume
34
First Page
12532
Last Page
12540
ISBN
9781577358350
Identifier
10.1609/aaai.v34i07.6942
Publisher
AAAI
City or Country
USA
Citation
XU, Xuemiao; LI, Keke; XU, Cheng; and HE, Shengfeng.
GDFace: Gated deformation for multi-view face image synthesis. (2020). Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, 2020 February 7-12. 34, 12532-12540.
Available at: https://ink.library.smu.edu.sg/sis_research/8520
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons