CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network
arXiv:1908.01166
Abstract
Convolutional Sparse Coding (CSC) has been attracting more and more attention in recent years, for making full use of image global correlation to improve performance on various computer vision applications. However, very few studies focus on solving CSC based image Super-Resolution (SR) problem. As a consequence, there is no significant progress in this area over a period of time. In this paper, we exploit the natural connection between CSC and Convolutional Neural Networks (CNN) to address CSC based image SR. Specifically, Convolutional Iterative Soft Thresholding Algorithm (CISTA) is introduced to solve CSC problem and it can be implemented using CNN architectures. Then we develop a novel CSC based SR framework analogy to the traditional SC based SR methods. Two models inspired by this framework are proposed for pre-/post-upsampling SR, respectively. Compared with recent state-of-the-art SR methods, both of our proposed models show superior performance in terms of both quantitative and qualitative measurements.
arXiv comment10 pages, 12 figures, 3 tables
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Sketch-based Manga Retrieval using Manga109 Dataset
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- A survey of sparse representation: algorithms and applications
- Residual Dense Network for Image Super-Resolution
- Convolutional Dictionary Learning: A Comparative Review and New Algorithms
- MemNet: A Persistent Memory Network for Image Restoration
- Learned Convolutional Sparse Coding
- Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding
- Deep Networks for Image Super-Resolution with Sparse Prior
- Deep Learning for Image Super-resolution: A Survey
- Deeply-Recursive Convolutional Network for Image Super-Resolution