Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

1-2021

Abstract

Face synthesis is an interesting yet challenging task in computer vision. It is even much harder to generate a portrait video than a single image. In this paper, we propose a novel video generation framework for synthesizing arbitrary-length face videos without any face exemplar or landmark. To overcome the synthesis ambiguity of face video, we propose a divide-and-conquer strategy to separately address the video face synthesis problem from two aspects, face identity synthesis and rearrangement. To this end, we design a cascaded network which contains three components, Identity-aware GAN (IA-GAN), Face Coherence Network, and Interpolation Network. IA-GAN is proposed to synthesize photorealistic faces with the same identity from a set of noises. Face Coherence Network is designed to re-arrange the faces generated by IA-GAN while keeping the inter-frame coherence. Interpolation Network is introduced to eliminate the discontinuity between two adjacent frames and improve the smoothness of the face video. Experimental results demonstrate that our proposed network is able to generate face video with high visual quality while preserving the identity. Statistics show that our method outperforms state-of-the-art unconditional face video generative models in multiple challenging datasets.

Keywords

Interpolation, Cascaded networks, Coherence networks, Divide and conquer, Generative model, State of the art, Three component, Video generation, Visual qualities

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Information Systems and Management

Publication

2020 25th International Conference on Pattern Recognition (ICPR)

ISBN

9781728188089

Identifier

10.1109/ICPR48806.2021.9412380

City or Country

USA

Copyright Owner and License

Authors

Download

Share

COinS