Large receptive field convolutional neural network for image super-resolution

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Large receptive field convolutional neural network for image super-resolution
	Cong Y(丛杨); Fan HJ(范慧杰); Tang YD(唐延东); Wang Q(王强)
	2017
会议名称	2017 IEEE International Conference on Image Processing (ICIP)
会议日期	September 17-20, 2017
会议地点	Beijing, China
关键词	Super resolution Convolutional neural network Receptive field Multi-scale
页码	958-962
通讯作者	Wang Q(王强)
中文摘要	This paper presents a new approach to Single Image Super Resolution (SISR), based upon Convolutional Neural Network (CNN). Although the SISR is ill-posed which can be seen as finding a non-linear mapping from a low to high dimensional space. Deep learning techniques have been successfully applied in many areas of computer vision, including low-level image restoration and non-linear mapping problems. We consider the single image Super-Resolution (SR) problem as convolution operators and develop a CNN to capture the characteristics of Low-Resolution (LR) input image. We find that increasing the receptive field shows the improvement in accuracy. Our solution is to establish the connection between traditional optimization-based schemes and neural network architectures. In the paper a novel, separable structure is introduced as a reliable support for robust convolution against artifacts. Our proposed method performs better than existing methods in terms of accuracy and visual improvements in our results are easily noticeable.
收录类别	EI ; CPCI（ISTP）
产权排序	1
会议主办者	The Institute of Electrical and Electronics Engineers Signal Processing Society
会议录	2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISSN号	1522-4880
ISBN号	978-1-5090-2175-8
WOS记录号	WOS:000428410701017
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/21350]
专题	沈阳自动化研究所_机器人学研究室
作者单位	1.Graduate University of the Chinese Academy of Science, Beijing 100049, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science, Shenyang 110016, China
推荐引用方式 GB/T 7714	Cong Y,Fan HJ,Tang YD,et al. Large receptive field convolutional neural network for image super-resolution[C]. 见:2017 IEEE International Conference on Image Processing (ICIP). Beijing, China. September 17-20, 2017.