申请试用
HOT
登录
注册
 
Deeply-Recursive Convolutional Network for Image Super-Resolution

Deeply-Recursive Convolutional Network for Image Super-Resolution

Reboot
/
发布于
/
1954
人观看
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 recur sions). Increasing recursion depth can improve perfor mance 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.
8 点赞
1 收藏
0下载
相关文档
确认
3秒后跳转登录页面
去登陆