Deeply-Recursive Convolutional Network for Image Super-Resolution
This addresses image super-resolution for computer vision applications, but it is incremental as it builds on existing recursive and convolutional network approaches.
The paper tackles the problem of image super-resolution by proposing a deeply-recursive convolutional network (DRCN) with up to 16 recursions, which improves performance without adding parameters, and it outperforms previous methods by a large margin.
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.