Deeply-Recursive Convolutional Network for Image Super-Resolution

Abstract

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.

CVPR 2016 Oral

References in corpus (3)

• Fully Convolutional Networks for Semantic Segmentation
• MatConvNet - Convolutional Neural Networks for MATLAB
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units

Cited by in corpus (21)

• Residual Dense Network for Image Super-Resolution
• Is the deconvolution layer the same as a convolutional layer?
• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
• Fast and Accurate Single Image Super-Resolution via Information Distillation Network
• Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution
• Convolutional Neural Pyramid for Image Processing
• Exploring Deep Learning Image Super-Resolution for Iris Recognition
• Deep Back-Projection Networks For Super-Resolution
• Learning Dual Convolutional Neural Networks for Low-Level Vision
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution
• Learning to Extract a Video Sequence from a Single Motion-Blurred Image
• Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting
• Deep Residual Network for Joint Demosaicing and Super-Resolution
• CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network
• Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution
• Generic 3D Convolutional Fusion for image restoration
• Theory of Generative Deep Learning : Probe Landscape of Empirical Error via Norm Based Capacity Control
• Content-adaptive Representation Learning for Fast Image Super-resolution