Please use this identifier to cite or link to this item:
Title: Real-time arbitrary style transfer via deep learning
Authors: Wang, Zijian
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Wang, Z. (2021). Real-time arbitrary style transfer via deep learning. Final Year Project (FYP), Nanyang Technological University, Singapore.
Project: SCSE20-0408
Abstract: Neural style transfer is the process of merging the content of one image with the style of another to create a new image. Many applications have recently exploited style transfer to create highly popular content on social media. Existing methods typically face limitations such as a small number of transferable styles and a sluggish image generation speed. In this work, we discuss two approaches, AdaIN and MUNIT, to achieve real-time arbitrary style transfer and apply it to videos. The AdaIN method can produce aesthetically pleasing stylized images by changing the content-style weight ratio. It is found that the AdaIN method can be sped up by eliminating convolutional layers from the decoder. The refined decoder of AdaIN achieves a large speed boost without compromising image quality of style transfer. The MUNIT method has advantages when training on a small dataset that style and content samples are from two specific domains. We analyze these two methods and derive possible theoretical reasons behind them. Since the refined AdaIN method only needs to be trained once and can produce stylized images at real-time speed, its application can be extended to perform real-time arbitrary video style transfer. Finally, we conclude with more discussions about several future improvement directions.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP final amended report_Wang Zijian.pdf
  Restricted Access
3.17 MBAdobe PDFView/Open

Page view(s)

Updated on May 15, 2022

Download(s) 50

Updated on May 15, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.