Abstract
Cartoon portraits are deformed figures that capture the appearance and characteristics of people, and are often used to express one’s image in applications such as social media, games, application profiles, and avatars. Current research regarding the translation of facial images into cartoon portraits focuses on translation methods that use unsupervised learning and methods for translating each part individually. However, studies that reflect the unique personality of professional illustrators have yet to be published. In this study, we examine a suitable network for reflecting the unique personality of a professional illustrator. Specifically, we will consider four networks: pix2pix, Cycle Generative Adversarial Network (CycleGAN), Paired CycleGAN, and Cyclepix. The main difference between these is the loss function. Pix2pix takes the error between the training data and the generated data. However, the main difference in CycleGAN is that it takes the error between the input data and the re-converted data obtained by further translating the generated data. Cyclepix takes both errors. Additionally, pix2pix and Paired CycleGAN require that the input of the discriminator be input data and generated data pairs. The difference between CycleGAN and Cyclepix is that only the input of the discriminator is generated data. Using the cycle consistency loss, considering only the input of the discriminator as generated data, and using the L1 Loss for supervised learning, the experimental results showed that the evaluation of CycleGAN and Cyclepix was high. This is useful for generating high-precision cartoon portraits.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
photoprocessing.com. http://www.photo-kako.com/likeness.cgi. Accessed 18 Feb 2019
Wu, Y., Enomoto, M., Ohya, J.: Study of subjective discrimination in an automatic system for generating line drawing based portraits from facial images. In: FIT2014, 13th Information Science and Technology Forum, 3rd volume, pp. 247–248 (2015)
Li, W., Xiong, W., Liao, H., Huo, J., Gao, Y., Luo, J.: CariGAN: caricature generation through weakly paired adversarial learning. arXiv:1811.00445 (2018)
Yi, R., Liu, Y.-J.: APDrawingGAN: generating artistic portrait drawings from face photos with hierarchical GANs. In: CVPR 2019, pp. 0743–10752 (2019)
Goodfellow, I.: NIPS 2016 tutorial: generative adversarial networks. arXiv:1701.00160 (2016)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)
Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Nakashima, Y., Bannai, Y. (2020). A Comparison of Cartoon Portrait Generators Based on Generative Adversarial Networks. In: Yamamoto, S., Mori, H. (eds) Human Interface and the Management of Information. Interacting with Information. HCII 2020. Lecture Notes in Computer Science(), vol 12185. Springer, Cham. https://doi.org/10.1007/978-3-030-50017-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-50017-7_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50016-0
Online ISBN: 978-3-030-50017-7
eBook Packages: Computer ScienceComputer Science (R0)