Visible to the public Combined Layer GAN for Image Style Transfer*

TitleCombined Layer GAN for Image Style Transfer*
Publication TypeConference Paper
Year of Publication2019
AuthorsZhou, Z., Yang, Y., Cai, Z., Yang, Y., Lin, L.
Conference Name2019 IEEE International Conference on Computational Electromagnetics (ICCEM)
Date PublishedMarch 2019
ISBN Number978-1-5386-7111-5
Keywordscolor constrains, color tune, combined layer GAN, Computer vision, Conferences, constraint, deep network, edge, edge detection, edge-constraint, Gallium nitride, GAN based image translation, generative adversarial networks, Generators, Image color analysis, image colour analysis, Image edge detection, image mapping, image style transfer, Metrics, neural nets, neural style transfer, pubcrawl, resilience, Resiliency, Scalability

Image style transfer is an increasingly interesting topic in computer vision where the goal is to map images from one style to another. In this paper, we propose a new framework called Combined Layer GAN as a solution of dealing with image style transfer problem. Specifically, the edge-constraint and color-constraint are proposed and explored in the GAN based image translation method to improve the performance. The motivation of the work is that color and edge are fundamental vision factors for an image, while in the traditional deep network based approach, there is a lack of fine control of these factors in the process of translation and the performance is degraded consequently. Our experiments and evaluations show that our novel method with the edge and color constrains is more stable, and significantly improves the performance compared with the traditional methods.

Citation Keyzhou_combined_2019