Enhanced Deep Residual Networks for Single Image Super-Resolution

被引：4777

作者：

Lim, Bee ^{[1
]}

Son, Sanghyun ^{[1
]}

Kim, Heewon ^{[1
]}

Nah, Seungjun ^{[1
]}

Lee, Kyoung Mu ^{[1
]}

机构：

[1] Seoul Natl Univ, Dept ECE, ASRI, Seoul 08826, South Korea

来源：

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) | 2017年

关键词：

D O I：

10.1109/CVPRW.2017.151

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance. In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods. The significant performance improvement of our model is due to optimization by removing unnecessary modules in conventional residual networks. The performance is further improved by expanding the model size while we stabilize the training procedure. We also propose a new multi-scale deep super-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model. The proposed methods show superior performance over the state-of-the-art methods on benchmark datasets and prove its excellence by winning the NTIRE2017 Super-Resolution Challenge [26].

引用

页码：1132 / 1140

页数：9