FAU  >  Technische Fakultät  >  Informatik  >  Lehrstuhl 15 (Digital Reality)

Digital Reality

 
[Pose Manipulation with Identity Preservation]

Pose Manipulation with Identity Preservation

Andrei-Timotei Ardelean1,  Lucian Sasu1,2

1 Transilvania University of Brasov
2 Xperi Corporation

Abstract

This paper describes a new model which generates images in novel poses e.g. by altering face expression and orientation, from just a few instances of a human subject. Unlike previous approaches which require large datasets of a specific person for training, our approach may start from a scarce set of images, even from a single image. To this end, we introduce Character Adaptive Identity Normalization GAN (CainGAN) which uses spatial characteristic features extracted by an embedder and combined across source images. The identity information is propagated throughout the network by applying conditional normalization. After extensive adversarial training, CainGAN receives figures of faces from a certain individual and produces new ones while preserving the person's identity. Experimental results show that the quality of generated images scales with the size of the input set used during inference. Furthermore, quantitative measurements indicate that CainGAN performs better compared to other methods when training data is limited.

Citation Style:    Publication

Pose Manipulation with Identity Preservation.
Andrei-Timotei Ardelean, Lucian Sasu.
International Journal of Computers Communications & Control.Andrei-Timotei Ardelean and Lucian Sasu. Pose manipulation with identity preservation. International Journal of Computers Communications & Control, 15(2), 2020.Ardelean, A.-T., and Sasu, L. 2020. Pose manipulation with identity preservation. International Journal of Computers Communications & Control 15, 2.A.-T. Ardelean and L. Sasu, “Pose manipulation with identity preservation,”International Journal of Computers Communications & Control, vol. 15, no. 2, 2020. [Online]. Available: http://univagora.ro/jour/index.php/ijccc/article/view/3862
thumbnail
Project Page
thumbnailPDF
BibTeXBibTeXBibTeX
thumbnail
DOI

Acknowledgments

Special thanks go to Xperi Corporation that provided the environment and physical resources that made this work possible.


Privacy: This page is free of cookies or any means of data collection. Copyright disclaimer: The documents contained in these pages are included to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.