CASIA OpenIR  > 模式识别实验室
CFFT-GAN: Cross-Domain Feature Fusion Transformer for Exemplar-Based Image Translation
Tianxiang Ma1,2; Bingchuan Li3; Wei Liu3; Miao Hua3; Jing Dong2; Tieniu Tan2,4
2023
Conference NameAAAI Conference on Artificial Intelligence
Conference Date2.7-2.14
Conference Place美国华盛顿
Abstract

Exemplar-based image translation refers to the task of generating images with the desired style, while conditioning on certain input image. Most of the current methods learn the correspondence between two input domains and lack the mining of information within the domains. In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions. Specifically, we propose a Cross-domain Feature Fusion Transformer (CFFT) to learn inter- and intra-domain feature fusion. Based on CFFT, the proposed CFFT-GAN works well on exemplar-based image translation. Moreover, CFFTGAN is able to decouple and fuse features from multiple domains by cascading CFFT modules. We conduct rich quantitative and qualitative experiments on several image translation tasks, and the results demonstrate the superiority of our approach compared to state-of-the-art methods. Ablation studies show the importance of our proposed CFFT. Application experimental results reflect the potential of our method.

Sub direction classification图像视频处理与分析
planning direction of the national heavy laboratory视觉信息处理
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56665
Collection模式识别实验室
Corresponding AuthorJing Dong
Affiliation1.School of Artificial Intelligence, University of Chinese Academy of Sciences
2.CRIPAC & NLPR, Institute of Automation, Chinese Academy of Sciences
3.ByteDance Ltd, Beijing, China
4.Nanjing University
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Tianxiang Ma,Bingchuan Li,Wei Liu,et al. CFFT-GAN: Cross-Domain Feature Fusion Transformer for Exemplar-Based Image Translation[C],2023.
Files in This Item:
File Name/Size DocType Version Access License
CFFT-GAN Cross-Domai(4072KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tianxiang Ma]'s Articles
[Bingchuan Li]'s Articles
[Wei Liu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tianxiang Ma]'s Articles
[Bingchuan Li]'s Articles
[Wei Liu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tianxiang Ma]'s Articles
[Bingchuan Li]'s Articles
[Wei Liu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CFFT-GAN Cross-Domain Feature Fusion Transformer for Exemplar-Based.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.