DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization

doi:10.1109/TNNLS.2023.3342645

	DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization
	Huang, Nisha 1,2; Zhang, Yuxin 1,2; Tang, Fan 3; Ma, Chongyang 4; Huang, Haibin 2; Dong, Weiming 1,2; Xu, Changsheng 1,2
	2024-01-10
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	14
摘要	Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user. Unlike the previous image-to-image transfer approaches, text-guided stylization progress provides users with a more precise and intuitive way to express the desired style. However, the huge discrepancy between cross-modal inputs/outputs makes it challenging to conduct text-driven image stylization in a typical feed-forward CNN pipeline. In this article, we present DiffStyler, a dual diffusion processing architecture to control the balance between the content and style of the diffused results. The cross-modal style information can be easily integrated as guidance during the diffusion process step-by-step. Furthermore, we propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image. We validate the proposed DiffStyler beyond the baseline methods through extensive qualitative and quantitative experiments. The code is available at https://github.com/haha-lisa/Diffstyler.
关键词	Arbitrary image stylization diffusion textual guidance neural network applications
DOI	10.1109/TNNLS.2023.3342645
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001173965600001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38847
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Dong, Weiming
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 4.Kuaishou Technol, Beijing 100085, Peoples R China
推荐引用方式 GB/T 7714	Huang, Nisha,Zhang, Yuxin,Tang, Fan,et al. DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2024:14.
APA	Huang, Nisha.,Zhang, Yuxin.,Tang, Fan.,Ma, Chongyang.,Huang, Haibin.,...&Xu, Changsheng.(2024).DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,14.
MLA	Huang, Nisha,et al."DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2024):14.