Creative Image Synthesis Using Neural Style Transfer Techniques

Priyanka Vashisht; Anvesha Katti

doi:10.55524/ijirem.2025.12.2.23

Abstract

First Art generation, a profound display of human creativity, evolves with technological advancements, notably in deep learning. One striking innovation is Neural Style Transfer (NST), blending artistical flair with technological prowess. NST employs convolutional neural networks, such as VGG19, to fuse the content of one image with the style of another, yielding captivating artworks. VGG19, a seminal CNN architecture, features 3x3 convolutional filters, max-pooling layers, and Rectified Linear Unit (ReLU) activations, enabling it to discern both low-level and high-level features. Through rigorous evaluation, the model demonstrates remarkable accuracy, precision, and recall. This project underscores NST's potential as a conduit for creative exploration, harmonizing traditional artistic techniques with AI capabilities

Keywords

CNN, Deep learning, image generation, neural style transfer, Transfer Learning, VGG19.

References

[1] L. A. Gatys, A. S. Ecker, and M. Bethge, "A Neural Algorithm of Artistic Style," arXiv preprint arXiv:1508.06576, 2015. Available from: https://doi.org/10.48550/arXiv.1508.06576

[2] D. Ulyanov, V. Lebedev, A. Vedaldi, and V. Lempitsky, "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images," in Proc. 33rd Int. Conf. Machine Learning (ICML), 2016, pp. 1349–1357.

[3] L. A. Gatys, A. S. Ecker, and M. Bethge, "Texture Synthesis Using Convolutional Neural Networks," in Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015.

[4] M. Ruder, A. Dosovitskiy, and T. Brox, "Artistic Style Transfer for Videos," in German Conf. Pattern Recognition (GCPR), 2016, pp. 26–36. Available from: https://doi.org/10.1007/978-3-319-45886-1_3

[5] J. Johnson, A. Alahi, and L. Fei-Fei, "Perceptual Losses for Real-Time Style Transfer and Super-Resolution," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 694–711.

[6] V. Dumoulin, J. Shlens, and M. Kudlur, "A Learned Representation For Artistic Style," arXiv preprint arXiv:1610.07629, 2016. Available from: https://doi.org/10.48550/arXiv.1610.07629

[7] D. Ulyanov, A. Vedaldi, and V. Lempitsky, "Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6924–6932.

[8] A. W. Harley, A. Dosovitskiy, and T. Brox, "Demystifying Neural Style Transfer," in Proc. IEEE Int. Conf. Computer Vision (ICCV), 2017, pp. 4358–4366.

[9] D. Ulyanov, A. Vedaldi, and V. Lempitsky, "Instance Normalization: The Missing Ingredient for Fast Stylization," arXiv preprint arXiv:1607.08022, 2016.

[10]TensorFlow, "tf.keras.optimizers.Adam," Available from: https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/Adam.

[11] J. Scholz, C. Reinke, P. Andreae, and J. Gall, "Fast Stable Reinforcement Learning through Robust Value Function Approximation," in Proc. IEEE Int. Conf. Robotics and Automation (ICRA), 2018, pp. 3521–3526.

[12] OpenGenus, "VGG19 Architecture," Available from: https://iq.opengenus.org/vgg19-architecture/.

[13] X. Huang and S. Belongie, "Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization," arXiv preprint arXiv:1703.06868, 2017. Available from: https://doi.org/10.48550/arXiv.1703.06868.

[14] M. Ruder, A. Dosovitskiy, and T. Brox, "Artistic Style Transfer for Videos," in German Conf. Pattern Recognition (GCPR), 2016, pp. 26–36. Available from: https://doi.org/10.1007/978-3-319-45886-1_3

[15] X. Huang and S. Belongie, "Exploring the Structure of a Real-time, Arbitrary Neural Artistic Style Transfer System," in Proc. European Conf. Computer Vision (ECCV), 2017, pp. 167–182.

[16] D. Ulyanov, A. Vedaldi, and V. Lempitsky, "Artistic Style Transfer with Learned Convolutional Networks," arXiv preprint arXiv:1705.06830, 2017.

[17] C. Scholz, J. Peters, and A. A. Faisal, "Fast Stable Reinforcement Learning through Robust Value Function Approximation," in Proc. IEEE Int. Conf. Robotics and Automation (ICRA), 2017, pp. 3521–3526.

[18] L. A. Gatys, M. Bethge, A. Hertzmann, and E. Shechtman, "Preserving Color in Neural Artistic Style Transfer," arXiv preprint arXiv:1606.05897, 2016. Available from: https://doi.org/10.48550/arXiv.1606.05897

[19] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," arXiv preprint arXiv:1409.1556, 2014. Available from: https://doi.org/10.48550/arXiv.1606.05897

[20] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," arXiv preprint arXiv:1409.1556, 2014. Available from: https://doi.org/10.48550/arXiv.1409.1556

[21] D. P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," arXiv preprint arXiv:1412.6980, 2014. Available from: https://doi.org/10.48550/arXiv.1412.6980

Cites this article as

P. Vashisht, A. Katti, "Creative Image Synthesis Using Neural Style Transfer Techniques", International Journal of Innovative Research in Engineering & Management (IJIREM), Vol-12, Issue-2, Page No-145-153, 2025. Available from: https://doi.org/10.55524/ijirem.2025.12.2.23

Corresponding Author

Priyanka Vashisht

Associate Professor, Department of Computer Science & Engineering, Amity School of Engineering and Technology, Amity University, Gurugram, Haryana, India