Paper Title
Nonlocal Image Restoration and Super Resolution Using Convolutional Sparse Coding

Simultaneous sparse coding (SSC) and a convolutional sparse coding (CSC) both the approach have shown great potential in various low-level vision tasks, leading to several state-of-the-art image restoration techniques. Our CSC method involves three groups of parameters to be learned: (i) a set of filters to decompose the low resolution (LR) image into LR sparse feature maps; (ii) a mapping function to predict the high resolution (HR) feature maps from the LR ones; and (iii) a set of filters to reconstruct the HR images from the predicted HR feature maps via simple convolution operations. In variance estimation perspective, namely that decomposition of similar packed patches can be viewed as pooling both local and nonlocal information for estimating signal variances. Such perspective inspires us to develop a new class of image restoration algorithms based on CSV approach. Our subjective quality results compare favorably with those obtained by existing techniques, especially at high noise levels and with a large amount of missing data. Keywords- Convolutional sparse coding (CSC), iterative regularization, low-rank method, simultaneous sparse coding, singular-value thresholding.