QQ客服 官方微博 反馈留言

	Image Inpainting via Enhanced Generative Adversarial Network
	Wang Q(王强)1,2; Fan HJ(范慧杰)1
	2021
会议日期	November 26-28, 2021
会议地点	Shanghai, China
页码	641-646
英文摘要	In this paper, we propose an Enhanced Generative Model for Image Inpainting (EGMII). Unlike most state-of-the-art algorithms using extra constraints to enforce the generator network recover semantic texture details, we construct an end-to-end network to generate both the image contents and high-frequency details progressively. Our model contains a two-phase generator and two discriminators. In our generator, the previous phase restores the structure information via convolutional encoder-decoder architecture, and the following phase captures high-frequency details via residual learning. For each generator phase, we define different objective functions and further optimize the entire network via a feed-forward manner. Moreover, for the generator in the second phase, we adopt a deep residual architecture, which also can eliminate the perceptual discontinuity on the border of the missing region. Experimental results on several public datasets demonstrate qualitatively and quantitatively that our model performs better than the state-of-the-art algorithms and can generate both realistic image contents and high-frequency details. Our code will be released soon.
产权排序	2
会议录	2021 27th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2021
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISBN号	978-1-6654-3153-8
WOS记录号	WOS:000783817900109
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/30501]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Fan HJ(范慧杰)
作者单位	1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2.Key Laboratory of Manufacturing Industrial Integrated, Shenyang University
推荐引用方式 GB/T 7714	Wang Q,Fan HJ. Image Inpainting via Enhanced Generative Adversarial Network[C]. 见:. Shanghai, China. November 26-28, 2021.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。