← Back to papers
2016 CVPR CVPR 2016

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.

🌉 Interdisciplinary Bridge — Computer Vision and Deep Learning and Machine Learning
🧭 Keyword Pioneer — recursive network
🐣 Hot Topic Early Bird — image super-resolution
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Jiwon Kim , Jung Kwon Lee , Kyoung Mu Lee

Topics

Machine Learning > Optimization & Theory > Neural Network Optimization Computer Vision > Processing > Image Restoration Deep Learning > Architectures > Convolutional Neural Networks

Keywords

deep learning image super-resolution gradient descent convolutional neural network recursive neural network convolutional network skip connection recursive network
Download PDF

Related papers

Joint Multiview Segmentation and Localization of RGB-D Images Using Depth-Induced Silhouette Consistency 2016
Unbiased Photometric Stereo for Colored Surfaces: A Variational Approach 2016
Deep Compositional Captioning: Describing Novel Object Categories Without Paired Training Data 2016
Stacked Attention Networks for Image Question Answering 2016
Neural Module Networks 2016