Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding
This is an incremental improvement for image super-resolution, enhancing interpretability and performance in a specific domain.
The paper tackles single image super-resolution by combining residual learning and convolutional sparse coding, resulting in a 30-layer model that outperforms recent state-of-the-art methods like DRRN and MemNet in accuracy and visual quality.
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.