Deeply-Recursive Convolutional Network for Image Super-Resolution

被引：32

作者：

Kim, Jiwon ^{[1
]}

Lee, Jung Kwon ^{[1
]}

Lee, Kyoung Mu ^{[1
]}

机构：

[1] Seoul Natl Univ, ASRI, Dept ECE, Seoul, South Korea

来源：

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2016年

关键词：

D O I：

10.1109/CVPR.2016.181

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advantages, learning a DRCN is very hard with a standard gradient descent method due to exploding/vanishing gradients. To ease the difficulty of training, we propose two extensions: recursive-supervision and skip-connection. Our method outperforms previous methods by a large margin.

引用

页码：1637 / 1645

页数：9

共 50 条

[41] Wavelet-Based Dual Recursive Network for Image Super-Resolution
Xin, Jingwei
Li, Jie
Jiang, Xinrui
Wang, Nannan
Huang, Heng
Gao, Xinbo
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (02) : 707 - 720
[42] Non-Global Shared Recursive Network for Image Super-Resolution
Zheng, Bing
Ma, Lihong
[J]. 2020 4TH INTERNATIONAL CONFERENCE ON MACHINE VISION AND INFORMATION TECHNOLOGY (CMVIT 2020), 2020, 1518
[43] Image Inpainting and Super-Resolution Using Non-local Recursive Deep Convolutional Network with Skip Connections
Liu, Miaofeng
[J]. NINTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2017), 2017, 10420
[44] Image Super-Resolution Reconstruction Based on Recursive Multi-scale Convolutional Networks
Gao, Qingqing
Zhao, Jianwei
Zhou, Zhenghua
[J]. Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2020, 33 (11): : 972 - 980
[45] Dynamic Multi-mapping Convolutional Network for Image Super-Resolution
Wang, Shiping
Bi, Duyan
He, Linyuan
Wang, Chen
Fan, Zunlin
Ding, Wenshan
Liu, Kun
[J]. 2018 IEEE 3RD INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP), 2018, : 276 - 280
[46] Image Super-Resolution Based on Error Compensation with Convolutional Neural Network
Lu, Wei-Ting
Lin, Chien-Wei
Kuo, Chih-Hung
Tung, Ying-Chan
[J]. 2017 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC 2017), 2017, : 1160 - 1163
[47] A two-channel convolutional neural network for image super-resolution
Li, Sumei
Fan, Ru
Lei, Guoqing
Yue, Guanghui
Hou, Chunping
[J]. NEUROCOMPUTING, 2018, 275 : 267 - 277
[48] ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution
Shen, Jialiang
Wang, Yucheng
Zhang, Jian
[J]. MOBILE NETWORKS & APPLICATIONS, 2021, 26 (01): : 13 - 26
[49] Image Super-resolution Reconstruction Algorithm Based on Convolutional Neural Network
He Jingxuan
Zhang Jian
Zhang Yonghui
Wang Rong
[J]. PROCEEDINGS OF 2018 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION, ELECTRONICS AND ELECTRICAL ENGINEERING (AUTEEE), 2018, : 267 - 271
[50] Single Image Super-Resolution using Adaptive Upsampling Convolutional Network
Liu, Peng
Hong, Ying
Liu, Yan
[J]. PROCEEDINGS OF 2019 IEEE 8TH JOINT INTERNATIONAL INFORMATION TECHNOLOGY AND ARTIFICIAL INTELLIGENCE CONFERENCE (ITAIC 2019), 2019, : 726 - 730

← 1 2 3 4 5 →