Controlled Face Generation System using StyleGAN2 Neural Network

Main Article Content

Marat Isangulov
Razil Minneakhmetov
Almaz Khamedzhanov
Timur Khafizyanov
Emil Pashaev
Ernest Kalimullin

Abstract

A novel approach to supervised face generation using open-source generative models including StyleGAN2 and Ridge Regression is presented. A methodology that extends StyleGAN2 to control facial characteristics such as age, race, gender, facial expression, and hair attributes is developed, and an extensive dataset of human faces with attribute annotations is utilized. The faces were encoded in 256-dimensional latent space using the StyleGAN2 encoder, resulting in a set of characteristic latent codes. We applied the t-SNE algorithm to cluster these feature-based codes, demonstrated the ability to control face generation, and subsequently trained Ridge regression models for each dimension of the latent codes using the labeled features. When decoded using StyleGAN2, the resulting codes successfully reconstructed face images while maintaining the association with the input features. The developed approach provides an easy and efficient way to supervised face generation using existing generative models such as StyleGAN2, and opens up new possibilities for different application areas.

Article Details

References

1. Xia W., Zhang Y., Yang Y., Xue J.-H., Zhou B., Yang M.-H. GAN Inversion: A Survey. ArXiv210105278 Cs. 2022. URL: http://arxiv.org/abs/2101.05278
2. Bishop C. Pattern Recognition and Machine Learning. Information Science and Statistics. 2006. URL: https://link.springer.com/book/9780387310732
3. Karras T., Laine S., Aila T. A Style-Based Generator Architecture for Generative Adversarial Networks. ArXiv181204948 Cs Stat. 2019. URL: http://arxiv.org/abs/1812.04948
4. Karras T., Hellsten J et al. Analyzing and Improving the Image Quality of StyleGAN. arXiv:1912.04958 Cs. 2019. URL: https://arxiv.org/pdf/1912.04958.pdf
5. Kryuchkov M., Khanzhina N., Osmakov I., Ulyanov P. CT images GAN-based augmentation with AdaIN for lung nodules detection // Proceedings of SPIE – The International Society for Optical Engineering: 13, Rome, 02–06 November 2020. Rome, 2020. P. 1160526. https://doi.org/10.1117/12.2587940–EDN JYZOEO.
6. Huang G., Ramesh M., Berg T., Learned-Miller E. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. University of Massachusetts, Amherst, Technical Report 07-49. 2018. URL: http://vis-www.cs.umass.edu/lfw/
7. Viola P., Jones M. Robust Real-time Object Detection. Second international workshop on statistical and computational theories of vision. 2001. URL: https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers
8. Ledig C., Theis L. et al. Photo-realistic single image super-resolution using a generative adversarial network. ArXiv:1609.04802v5 Cs. 2016. URL: https://arxiv.org/pdf/1609.04802v5.pdf
9. Goar V., Kuri M., Kumar R., Senjyu T. Data Compression and Visualization Using PCA and T-SNE. Advances in Information Communication Technology and Computing. 2019. URL: https://www.researchgate.net/publication/344000619_Data_Compression_ and_Visualization_Using_PCA_and_T-SNE
10. Kolo B. Binary and Multiclass Classification. Weatherford Press. 2010. URL: https://www.amazon.com/Binary-Multiclass-Classification-Brian-Kolo/dp/1615800131
11. Rawlings J., Pantula S., Dickey D. Polynomial Regression. Applied Regression Analysis. 1998. URL: https://link.springer.com/chapter/10.1007/0-387-22753-9_8
12. Козина Н. И., Шиян Н. В., Чалченко М. Р. Современные достижения в области генерации изображений на примере нейронной сети MIDJOURNEY // Сборник материалов XVI-ой международной очно-заочной научно-практической конференции. М.: Научно-издательский центр «Империя», 2023. С. 121–125.


Most read articles by the same author(s)