International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Exploring the Evolution and Future Trends of Image Style Transfer Techniques: A Comprehensive Literature Review

Abstract

The rapid evolution of image style transfer techniques, a fascinating intersection of art and technology, represents a significant area of research in the domain of computer vision and machine learning. This comprehensive literature review critically examines the development and progression of various methodologies in image style transfer, tracing their evolution from initial neural algorithm-based approaches to more advanced generative adversarial networks (GANs) like CycleGAN, DiscoGAN, and StarGAN. By scrutinizing studies ranging from foundational works to recent innovative approaches, this paper aims to provide a thorough understanding of the techniques, their effectiveness, and the challenges they address. Emerging trends, such as the incorporation of domain-specific information, attention mechanisms, and human perception-inspired loss functions, are highlighted, reflecting the field's shift towards more context-aware and semantically meaningful image translations. The review identifies gaps in systematic comparative studies, particularly concerning the efficacy of CycleGANs against other prevalent methods, indicating areas ripe for future research. This paper serves as a foundational guide for understanding current image style transfer techniques and sets the stage for exploring new horizons in the blending of artistic creativity and technological innovation.

Country : Lebanon

1 Zainab Hussain Mahdi2 Kassem Danach3 Marwa Hamade

  1. Faculty of Engineering, Islamic University of Lebanon, Lebanon
  2. Faculty of Business Administration, Al Maaref University, Lebanon
  3. Faculty of Business Administration, Al Maaref University, Lebanon

IRJIET, Volume 8, Issue 6, June 2024 pp. 71-80

doi.org/10.47001/IRJIET/2024.806009

Full Paper
Download

References

  1. J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2223-2232.
  2. L. A. Gatys, A. S. Ecker, and M. Bethge, "A neural algorithm of artistic style," arXiv preprint arXiv:1508.06576, 2015.
  3. A.Radford, L. Metz, and S. Chintala, "Unsupervised representation learning with deep convolutional generative adversarial networks," arXiv preprint arXiv:1511.06434, 2015.
  4. P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, "Image-to-image translation with conditional adversarial networks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1125-1134.
  5. T. Kim, M. Cha, H. Kim, J. K. Lee, and J. Kim, "Learning to discover cross-domain relations with generative adversarial networks," in International conference on machine learning, 2017: PMLR, pp. 1857-1865.
  6. Y. Chen, M. Tang, C. W. Y. AG, and Y. V. Wang, "CycleGAN and Representation Disentanglement."
  7. Y. Choi, M. Choi, M. Kim, J.-W. Ha, S. Kim, and J. Choo, "Stargan: Unified generative adversarial networks for multi-domain image-to-image translation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8789-8797.
  8. S. Benaim and L. Wolf, "One-shot unsupervised cross domain translation," advances in neural information processing systems, vol. 31, 2018.
  9. F. Marra, D. Gragnaniello, L. Verdoliva, and G. Poggi, "Do gans leave artificial fingerprints?," in 2019 IEEE conference on multimedia information processing and retrieval (MIPR), 2019: IEEE, pp. 506-511.
  10. Y. Wu, R. Zhang, and K. Yanai, "Attention Guided Unsupervised Image-to-Image Translation with Progressively Growing Strategy," in Asian Conference on Pattern Recognition, 2019: Springer, pp. 85-99.
  11. W. Zheng, L. Yan, C. Gou, and F.-Y. Wang, "JND-GAN: human-vision-systems inspired generative adversarial networks for image-to-image translation," in ECAI 2020: IOS Press, 2020, pp. 2816-2823.
  12. E. Batziou, P. Alvanitopoulos, K. Ioannidis, I. Patras, S. Vrochidis, and I. Kompatsiaris, "Cycle-consistent adversarial networks and fast adaptive bi-dimensional empirical mode decomposition for style transfer," in 2020 25th International Conference on Pattern Recognition (ICPR), 2021: IEEE, pp. 2360-2367.
  13. Z. Chen et al., "Pregan: Pose randomization and estimation for weakly paired image style translation," IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2209-2216, 2021.
  14. T. Fontanini, F. Botti, M. Bertozzi, and A. Prati, "Avoiding Shortcuts in Unpaired Image-to-Image Translation," in International Conference on Image Analysis and Processing, 2022: Springer, pp. 463-475.
  15. X. Rang, C. Ma, Q. Zheng, and G. Zhao, "A Generative Adversarial Network for Multistyle Unsupervised Image Transfer Based on Dynamic Position Normalization," IEEE Access, vol. 10, pp. 96284-96295, 2022.
  16. L. Wang, L. Wang, and S. Chen, "ESA‐CycleGAN: Edge feature and self‐attention based cycle‐consistent generative adversarial network for style transfer," IET Image Processing, vol. 16, no. 1, pp. 176-190, 2022.
  17. D. Wang, W. Yao, T. Jiang, W. Zhou, L. Lin, and X. Chen, "A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications," arXiv preprint arXiv:2304.10679, 2023.
  18. I.Abbasnejad et al., "SCONE-GAN: Semantic Contrastive Learning-Based Generative Adversarial Network for an End-to-End Image Translation," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1111-1120.

Copyright @ 2026-2017 IRJIET. All Right Reserved.

Developed by Byzero Technologies