International Journal of New Developments in Engineering and Society, 2024, 8(1); doi: 10.25236/IJNDES.2024.080101.
Liu Fenfen1, Zhu Zimin2
1Xi'an Peihua University, Xi'an, 710125, China
2Northeast Forestry University, Harbin, 150006, China
This paper presents a comprehensive exploration of image style transfer techniques and artistic creation algorithms utilizing Generative Adversarial Networks (GANs). The research is structured into three main sections. Firstly, an overview of traditional image style transfer techniques is provided, highlighting their strengths and limitations. Secondly, the fundamental concepts and architectures of GANs are discussed, elucidating their role in generating realistic and diverse images. Lastly, the fusion of GANs with image style transfer methodologies is examined, showcasing the synergistic potential of combining these two approaches for enhanced artistic creation. Through this interdisciplinary investigation, we aim to contribute to the advancement of computational creativity and visual aesthetics in the field of artificial intelligence.
Image style transfer, Generative adversarial networks, Artistic creation, Deep learning, Visual expression
Liu Fenfen, Zhu Zimin. Research on Image Style Transfer and Artistic Creation Algorithm Based on Generative Adversarial Networks. International Journal of New Developments in Engineering and Society (2024) Vol.8, Issue 1: 1-6. https://doi.org/10.25236/IJNDES.2024.080101.
[1] Chen, X., Xu, C., Yang, X., Song, L., & Tao, D. (2018). Gated-gan: Adversarial gated networks for multi-collection style transfer. IEEE Transactions on Image Processing, 28(2), 546-560.
[2] Zhang, F., & Wang, C. (2020). MSGAN: generative adversarial networks for image seasonal style transfer. IEEE Access, 8, 104830-104840.
[3] Chen, Y., Lai, Y. K., & Liu, Y. J. (2018). Cartoongan: Generative adversarial networks for photo cartoonization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9465-9474).
[4] Han, X., Wu, Y., & Wan, R. (2023). A Method for Style Transfer from Artistic Images Based on Depth Extraction Generative Adversarial Network. Applied Sciences, 13(2), 867.
[5] Wang, R. (2019). Research on image generation and style transfer algorithm based on deep learning. Open Journal of Applied Sciences, 9(08), 661.
[6] Liu, Y. (2021). Improved generative adversarial network and its application in image oil painting style transfer. Image and Vision Computing, 105, 104087.
[7] Xu, W., Long, C., Wang, R., & Wang, G. (2021). Drb-gan: A dynamic resblock generative adversarial network for artistic style transfer. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 6383-6392).