A styleGAN-based face de-morphing network for restoring accomplice's facial image.
Saved in:
| Title: | A styleGAN-based face de-morphing network for restoring accomplice's facial image. |
|---|---|
| Authors: | Cai, Juan1 (AUTHOR), Long, Min2 (AUTHOR) caslongm@aliyun.com, Zhang, Le-Bing1 (AUTHOR) zhanglebing@hhtc.edu.cn, Yao, Quantao3 (AUTHOR), Ding, Xiangling4 (AUTHOR) |
| Source: | Multimedia Systems. Oct2025, Vol. 31 Issue 5, p1-15. 15p. |
| Subjects: | Generative adversarial networks, Morphing (Computer animation), Biometric identification, Image reconstruction, Face perception, Encoding, Image processing |
| Abstract: | Face morphing attacks pose a significant threat to modern facial recognition systems by fusing two facial images into a single morphed image. This can deceive biometric systems and lead to inaccurate identifications. Despite various detection methods developed to counter these attacks, restoring the original facial image of the accomplice from the morphed image-known as face de-morphing-remains a substantial challenge. In this paper, we propose a StyleGAN-based face de-morphing network to recover the facial images of the accomplice. Our method utilizes the pre-trained StyleGAN model to encode facial images into the semantic latent space, applies a specially designed lightweight identity feature separation network to obtain high-quality semantic latent encodings of the accomplice, and then employs another pre-trained StyleGAN to generate high-quality restored images. Experimental results demonstrate that our approach significantly improves restoration accuracy compared to existing facial de-morphing methods while maintaining an efficient and lightweight identity separation network. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
