• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Lin, Qi (Lin, Qi.) | Zhu, Qing (Zhu, Qing.) | Li, Weiran (Li, Weiran.)

Indexed by:

CPCI-S EI Scopus

Abstract:

Image Style transfer techniques can be applied in many fields, such as artistic creation, film, and television special effects, etc. It is a hot and difficult research topic in image processing. With the rapid development of the mobile Internet, fantasy pictures created through style transfer and shared on social networking sites are very popular and hot. The style transfer algorithm based on CNN is the current mainstream method because of its speed and efficiency. However, the current style transfer methods mainly target the entire image and lack pertinence. In addition, these methods always over-transfer style features and lack the details of the main content of the picture, which affects the aesthetics of the resulting picture. In this paper, we mainly studies image layered style transfer technology and propose a new style transfer algorithm that can highlight the details of the ROI in the image by introducing the color transfer Reinhard algorithm which can enrich the diversity of style transfer methods and provide people with new creative methods.

Keyword:

style transfer image processing convolutional neural network Reinhard algorithm

Author Community:

  • [ 1 ] [Lin, Qi]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 2 ] [Zhu, Qing]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 3 ] [Li, Weiran]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China

Reprint Author's Address:

Show more details

Related Keywords:

Source :

2022 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, HUMAN-COMPUTER INTERACTION AND ARTIFICIAL INTELLIGENCE, VRHCIAI

Year: 2022

Page: 162-166

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 7

Affiliated Colleges:

Online/Total:606/10602549
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.