Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding
arXiv:1812.11950
Abstract
We propose a simple yet effective model for Single Image Super-Resolution (SISR), by combining the merits of Residual Learning and Convolutional Sparse Coding (RL-CSC). Our model is inspired by the Learned Iterative Shrinkage-Threshold Algorithm (LISTA). We extend LISTA to its convolutional version and build the main part of our model by strictly following the convolutional form, which improves the network's interpretability. Specifically, the convolutional sparse codings of input feature maps are learned in a recursive manner, and high-frequency information can be recovered from these CSCs. More importantly, residual learning is applied to alleviate the training difficulty when the network goes deeper. Extensive experiments on benchmark datasets demonstrate the effectiveness of our method. RL-CSC (30 layers) outperforms several recent state-of-the-arts, e.g., DRRN (52 layers) and MemNet (80 layers) in both accuracy and visual qualities. Codes and more results are available at https://github.com/axzml/RL-CSC.
10 pages, 8 figures, 4 tables
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Deep Learning for Single Image Super-Resolution: A Brief Review
- A survey of sparse representation: algorithms and applications
- Convolutional Dictionary Learning: A Comparative Review and New Algorithms
- Learned Convolutional Sparse Coding
- Fast Stochastic Alternating Direction Method of Multipliers