Image inpainting algorithm based on neural network and attention mechanism

	Image inpainting algorithm based on neural network and attention mechanism
	Li, Yu; Yu, Xiuyuan; Bao, Qiliang
	2019-12-20
会议日期	December 20, 2019 - December 22, 2019
会议地点	Sanya, China
DOI	10.1145/3377713.3377764
页码	345-349
英文摘要	At present, there are obvious defects in the two mainstream generation models VAE and GAN of deep learning in the field of image inpainting.Based on the advantages of both, the paper recommends conditional information and attention mechanism, proposesing the ACVAE-PGGAN network model, which draws on the progressive growth training method and performs lightweight compression.The experimental result shows that the improved network model proposed in paper enhances training stability, which improves the resolution of generated images and the number of running frames effectively. © 2019 ACM.
会议录	ACM International Conference Proceeding Series
会议录出版者	Association for Computing Machinery
文献子类	会议论文
语种	英语
内容类型	会议论文
源URL	[http://ir.ioe.ac.cn/handle/181551/9590]
专题	光电技术研究所_光电工程总体研究室（一室）
作者单位	Institute of Optics and Electronics, University of Chinese Academy of Sciences, Chengdu, China
推荐引用方式 GB/T 7714	Li, Yu,Yu, Xiuyuan,Bao, Qiliang. Image inpainting algorithm based on neural network and attention mechanism[C]. 见:. Sanya, China. December 20, 2019 - December 22, 2019.