Neural Style Transfer: A Review and Analysis

Jiacheng Cao

doi:10.54097/0jryvs42

Authors

Jiacheng Cao

DOI:

https://doi.org/10.54097/0jryvs42

Keywords:

neural style transfer; deep learning; Convolutional Neural Network.

Abstract

Neural style transfer (NST) is a fascinating deep learning application that merges the style of one image with the content of another, resulting in visually compelling artistic images. This article reviews multiple research advances in the field of NST, including new style loss based on Sliced Wasserstein distance, VTNet model for video style conversion, Graph Neural Network based image style transfer method, multi style geometric deformation method, 3D neural style conversion, style transfer for 3D grids, traditional Chinese painting style transfer, and artistic conversion of QR codes. Through these studies, the author aims to improve the effectiveness and efficiency of image and video style conversion while maintaining the integrity of content information. The newly proposed style loss function utilizes SWD to improve computational efficiency and theoretically ensures the accuracy of style similarity. VTNet introduces prediction and generation branches to achieve high-quality, real-time video style conversion. In addition, the article also explores semi parametric methods based on GNN, multi style geometric transformations, and style transfer techniques for specific cultural artworks, demonstrating the potential application of neural style transfer in different fields and its contribution to artistic creation and design.

Downloads

Download data is not yet available.

References

[1] Li J. Sliced Wasserstein Distance for Neural Style Transfer. Computers & graphics, 2022, 102 : 89–98.

[2] Xu K. Learning Self-Supervised Space-Time CNN for Fast Video Style Transfer. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2021, 30: 2501-2512.

[3] Jing Y C. Learning Graph Neural Networks for Image Style Transfer. Computer Vision - ECCV 2022, PT VII, 2022, 13667: 111 - 128.

[4] Alexandru I. Image Style Transfer via Multi-Style Geometry Warping. Applied sciences, 2022, 12(12)

[5] Friedrich T. Voxel-Based Three-Dimensional Neural Style Transfer. Advances in Computational Intelligence: 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, PT I, 2021, 12861: 334 - 346.

[6] Kang H Y. Neural Style Transfer for 3D Meshes. Graphical models. 2023, 129

[7] Chen W R. Chinese Character Style Transfer Model Based on Convolutional Neural Network. Artificial Neural Networks and Machine Learning -- ICANN 2022, PT IV, 2022, 13532: 558 - 569.

[8] Liu X H. Sound Transformation: Applying Image Neural Style Transfer Networks to Audio Spectograms. Computer Analysis of Images and Patterns: 18th International Conference, CAIP 2019, PT II, 2019, 11679: 330 - 341.

[9] Wu H. Direction-Aware Neural Style Transfer with Texture Enhancement. Neurocomputing, 2019, 370: 39–55.

[10] Sheng J C. Convolutional Neural Network Style Transfer Towards Chinese Paintings. IEEE access : practical innovations, open solutions, 2019, 7: 163719–163728.

[11] Li H S. Style Transfer for QR Code. Multimedia tools and applications, 2020, 79(45–46); 33839 - 33852.