Uncertainty-aware image inpainting with adaptive feedback network

doi:10.1016/j.eswa.2023.121148

	Uncertainty-aware image inpainting with adaptive feedback network
	Ma, Xin1 ; Zhou, Xiaoqiang 3,4; Huang, Huaibo3 ; Jia, Gengyun2 ; Wang, Yaohui 5; Chen, Xinyuan 5; Chen, Cunjian 1
发表期刊	EXPERT SYSTEMS WITH APPLICATIONS
ISSN	0957-4174
	2024
卷号	235 页码:8
通讯作者	Chen, Cunjian(cunjian.chen@monash.edu)
摘要	While most image inpainting methods perform well on small image defects, they still struggle to deliver satisfactory results on large holes due to insufficient image guidance. To address this challenge, this paper proposes an uncertainty-aware adaptive feedback network (U2AFN), which incorporates an adaptive feedback mechanism to refine inpainting regions progressively. U2AFN predicts both an uncertainty map and an inpainting result simultaneously. During each iteration, the adaptive integration feedback block utilizes inpainting pixels with low uncertainty to guide the subsequent learning iteration. This process leads to a gradual reduction in uncertainty and produces more reliable inpainting outcomes. Our approach is extensively evaluated and compared on multiple datasets, demonstrating its superior performance over existing methods. The code is available at: https://codeocean.com/capsule/1901983/tree.
关键词	Image inpainting Uncertainty estimation Feedback mechanism
DOI	10.1016/j.eswa.2023.121148
收录类别	SCI
语种	英语
资助项目	Faculty Initiatives Research, Monash University[2901912] ; NVIDIA Academic Hardware Grant Program ; National Key R&D Program of China[2022ZD0160100] ; Shanghai Committee of Science and Technology[21DZ1100100]
项目资助者	Faculty Initiatives Research, Monash University ; NVIDIA Academic Hardware Grant Program ; National Key R&D Program of China ; Shanghai Committee of Science and Technology
WOS研究方向	Computer Science ; Engineering ; Operations Research & Management Science
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science
WOS记录号	WOS:001063057000001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53168
专题	多模态人工智能系统全国重点实验室
通讯作者	Chen, Cunjian
作者单位	1.Monash Univ, Clayton, Australia 2.Nanjing Univ Posts & Telecommun, Sch Commun & Informat Engn, Nanjing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Nanjing, Peoples R China 4.Univ Sci & Technol China, Hefei, Peoples R China 5.Shanghai Artificial Intelligence Lab, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Ma, Xin,Zhou, Xiaoqiang,Huang, Huaibo,et al. Uncertainty-aware image inpainting with adaptive feedback network[J]. EXPERT SYSTEMS WITH APPLICATIONS,2024,235:8.
APA	Ma, Xin.,Zhou, Xiaoqiang.,Huang, Huaibo.,Jia, Gengyun.,Wang, Yaohui.,...&Chen, Cunjian.(2024).Uncertainty-aware image inpainting with adaptive feedback network.EXPERT SYSTEMS WITH APPLICATIONS,235,8.
MLA	Ma, Xin,et al."Uncertainty-aware image inpainting with adaptive feedback network".EXPERT SYSTEMS WITH APPLICATIONS 235(2024):8.