Deep Learning-Based Image and Video Inpainting: A Survey

doi:10.1007/s11263-023-01977-6

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Deep Learning-Based Image and Video Inpainting: A Survey
	Quan, Weize 1,2; Chen, Jiaxi 1,2; Liu, Yanli 3; Yan, Dong-Ming 1,2; Wonka, Peter 4
刊名	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2024-01-19
页码	34
关键词	Image inpainting Video inpainting Deep learning Content generation
ISSN号	0920-5691
DOI	10.1007/s11263-023-01977-6
通讯作者	Yan, Dong-Ming(yandongming@gmail.com)
英文摘要	Image and video inpainting is a classic problem in computer vision and computer graphics, aiming to fill in the plausible and realistic content in the missing areas of images and videos. With the advance of deep learning, this problem has achieved significant progress recently. The goal of this paper is to comprehensively review the deep learning-based methods for image and video inpainting. Specifically, we sort existing methods into different categories from the perspective of their high-level inpainting pipeline, present different deep learning architectures, including CNN, VAE, GAN, diffusion models, etc., and summarize techniques for module design. We review the training objectives and the common benchmark datasets. We present evaluation metrics for low-level pixel and high-level perceptional similarity, conduct a performance evaluation, and discuss the strengths and weaknesses of representative inpainting methods. We also discuss related real-world applications. Finally, we discuss open challenges and suggest potential future research directions.
资助项目	National Natural Science Foundation of China[62102418] ; National Natural Science Foundation of China[62172415] ; National Natural Science Foundation of China[61972271] ; Beijing Science and Technology Plan Project[Z231100005923033] ; Open Project Program of National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University[2021SCUVS002]
WOS关键词	REMOVAL ; TEXTURE ; NETWORK ; CLASSIFICATION ; FRAMEWORK ; SCALE
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:001144998000001
资助机构	National Natural Science Foundation of China ; Beijing Science and Technology Plan Project ; Open Project Program of National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54792]
专题	多模态人工智能系统全国重点实验室
通讯作者	Yan, Dong-Ming
作者单位	1.Chinese Acad Sci, Inst Automat, MAIS, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Sichuan Univ, Coll Comp Sci, Chengdu, Peoples R China 4.King Abdullah Univ Sci & Technol, Comp Elect & Math Sci & Engn Div, Thuwal, Saudi Arabia
推荐引用方式 GB/T 7714	Quan, Weize,Chen, Jiaxi,Liu, Yanli,et al. Deep Learning-Based Image and Video Inpainting: A Survey[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2024:34.
APA	Quan, Weize,Chen, Jiaxi,Liu, Yanli,Yan, Dong-Ming,&Wonka, Peter.(2024).Deep Learning-Based Image and Video Inpainting: A Survey.INTERNATIONAL JOURNAL OF COMPUTER VISION,34.
MLA	Quan, Weize,et al."Deep Learning-Based Image and Video Inpainting: A Survey".INTERNATIONAL JOURNAL OF COMPUTER VISION (2024):34.