中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Self-Prior Guided Pixel Adversarial Networks for Blind Image Inpainting

文献类型：期刊论文

作者Wang, Juan6; Yuan, Chunfeng6; Li, Bing1,6; Deng, Ying2; Hu, Weiming3,4,6; Maybank, Stephen5
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-10-01
卷号45期号:10页码:12377-12393
ISSN号0162-8828
关键词Blind image inpainting semantic-discontinuity detection layout map prediction pixel generative adversarial network
DOI10.1109/TPAMI.2023.3284431
通讯作者Li, Bing(bli@nlpr.ia.ac.cn)
英文摘要Blind image inpainting involves two critical aspects, i.e., "where to inpaint" and "how to inpaint". Knowing "where to inpaint" can eliminate the interference arising from corrupted pixel values; a good "how to inpaint" strategy yields high-quality inpainted results robust to various corruptions. In existing methods, these two aspects usually lack explicit and separate consideration. This paper fully explores these two aspects and proposes a self-prior guided inpainting network (SIN). The self-priors are obtained by detecting semantic-discontinuous regions and by predicting global semantic structures of the input image. On the one hand, the self-priors are incorporated into the SIN, which enables the SIN to perceive valid context information from uncorrupted regions and to synthesize semantic-aware textures for corrupted regions. On the other hand, the self-priors are reformulated to provide a pixel-wise adversarial feedback and a high-level semantic structure feedback, which can promote the semantic continuity of inpainted images. Experimental results demonstrate that our method achieves state-of-the-art performance in metric scores and in visual quality. It has an advantage over many existing methods that assume "where to inpaint" is known in advance. Extensive experiments on a series of related image restoration tasks validate the effectiveness of our method in obtaining high-quality inpainting.
WOS关键词COMPRESSION
资助项目National Key Research and Development Program of China ; Natural Science Foundation of China[2020AAA0106800] ; Natural Science Foundation of China[62202470] ; Natural Science Foundation of China[61972397] ; Natural Science Foundation of China[62122086] ; Natural Science Foundation of China[U1936204] ; Natural Science Foundation of China[62036011] ; Natural Science Foundation of China[62192782] ; Natural Science Foundation of China[61721004] ; Beijing Natural Science Foundation[U2033210] ; Beijing Natural Science Foundation[4224093] ; Beijing Natural Science Foundation[JQ21017] ; Major Projects of Guangdong Education Department for Foundation Research and Applied Research[L223003] ; Major Projects of Guangdong Education Department for Foundation Research and Applied Research[2017KZDXM081] ; Guangdong Provincial University Innovation Team Project[2018KZDXM066] ; Youth Innovation Promotion Association, CAS ; [2020KCXTD045]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE COMPUTER SOC
WOS记录号WOS:001068816800054
资助机构National Key Research and Development Program of China ; Natural Science Foundation of China ; Beijing Natural Science Foundation ; Major Projects of Guangdong Education Department for Foundation Research and Applied Research ; Guangdong Provincial University Innovation Team Project ; Youth Innovation Promotion Association, CAS
源URL[http://ir.ia.ac.cn/handle/173211/53068]  
专题多模态人工智能系统全国重点实验室
通讯作者Li, Bing
作者单位1.People AI Inc, Beijing 100080, Peoples R China
2.Nanchang Hangkong Univ, Sch Aeronaut Mfg Engn, Nanchang 330063, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
4.Shanghai Tech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
5.Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
6.Chinese Acad Sci CASIA, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Juan,Yuan, Chunfeng,Li, Bing,et al. Self-Prior Guided Pixel Adversarial Networks for Blind Image Inpainting[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(10):12377-12393.
APA Wang, Juan,Yuan, Chunfeng,Li, Bing,Deng, Ying,Hu, Weiming,&Maybank, Stephen.(2023).Self-Prior Guided Pixel Adversarial Networks for Blind Image Inpainting.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(10),12377-12393.
MLA Wang, Juan,et al."Self-Prior Guided Pixel Adversarial Networks for Blind Image Inpainting".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.10(2023):12377-12393.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。