SIA OpenIR  > 机器人学研究室
Large receptive field convolutional neural network for image super-resolution
Wang Q(王强); Fan HJ(范慧杰); Cong Y(丛杨); Tang YD(唐延东)
作者部门机器人学研究室
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
会议主办者The Institute of Electrical and Electronics Engineers Signal Processing Society
会议录名称2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
出版者IEEE
出版地New York
2017
页码958-962
收录类别EI ; CPCI(ISTP)
EI收录号20181605019641
WOS记录号WOS:000428410701017
产权排序1
ISSN号1522-4880
ISBN号978-1-5090-2175-8
关键词Super Resolution Convolutional Neural Network Receptive Field Multi-scale
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.
语种英语
引用统计
文献类型会议论文
条目标识符http://ir.sia.cn/handle/173321/21350
专题机器人学研究室
通讯作者Wang Q(王强)
作者单位1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science, Shenyang 110016, China
2.Graduate University of the Chinese Academy of Science, Beijing 100049, China
推荐引用方式
GB/T 7714
Wang Q,Fan HJ,Cong Y,et al. Large receptive field convolutional neural network for image super-resolution[C]//The Institute of Electrical and Electronics Engineers Signal Processing Society. New York:IEEE,2017:958-962.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
LARGE RECEPTIVE FIEL(486KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang Q(王强)]的文章
[Fan HJ(范慧杰)]的文章
[Cong Y(丛杨)]的文章
百度学术
百度学术中相似的文章
[Wang Q(王强)]的文章
[Fan HJ(范慧杰)]的文章
[Cong Y(丛杨)]的文章
必应学术
必应学术中相似的文章
[Wang Q(王强)]的文章
[Fan HJ(范慧杰)]的文章
[Cong Y(丛杨)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: LARGE RECEPTIVE FIELD CONVOLUTIONAL NEURAL NETWORK FOR IMAGE SUPER-RESOLUTION.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。