Skip to main content

Fast photographic style transfer based on convolutional neural networks.

Wang, L., Xiang, N., Yang, X. and Zhang, J. J., 2018. Fast photographic style transfer based on convolutional neural networks. In: Computer Graphics International (CGI), 11-14 June 2018, Bintan, Indonesia, 67 - 76.

Full text available as:

[img]
Preview
PDF
p67-Wang.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

6MB

DOI: 10.1145/3208159.3208165

Abstract

© 2018 ACM. The techniques for photographic style transfer have been researched for a long time, which explores effective ways to transfer the style features of a reference photo onto another content photograph. Recent works based on convolutional neural networks present an effective solution for style transfer, especially for paintings. The artistic style transformation results are visually appealing, however, the photorealism is lost because of content-mismatching and distortions even when both input images are photographic. To tackle this challenge, this paper introduces a similarity loss function and a refinement method into the style transfer network. The similarity loss function can solve the content-mismatching problem, however, the distortion and noise artefacts may still exist in the stylized results due to the content-style trade-off. Hence, we add a post-processing refinement step to reduce the artefacts. The robustness and effectiveness of our approach has been evaluated through extensive experiments which show that our method can obtain finer content details and less artefacts than state-of-the-art methods, and transfer style faithfully. In addition, our approach is capable of processing photographic style transfer in almost real-time, which makes it a potential solution for video style transfer.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Media & Communication
ID Code:32095
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:25 Mar 2019 14:02
Last Modified:25 Mar 2019 14:03

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -