As a powerful statistical signal modeling technique, sparse representation has been widely used in various image restoration (IR) applications. The sparsity-based methods have achieved leading performance in the past few decades. However, in recent years it has been surpassed by other methods, especially the recent deep learning based methods. In this paper, we address the question that whether sparse representation can be competitive again. The way we answer this question is to redesign it with a deep architecture. To be specific, we propose an end-to-end deep architecture that follows the process of the sparse representation based IR. In particular, we learn a sparse convolutional dictionary to replace the traditional dictionary, and a convolutional neural network (CNN) denoising prior to replace the image prior. Through end-to-end training, the parameters in convolutional dictionary and CNN denoiser can be jointly optimized. Experimental results on several representative IR tasks, including image denoising, deblurring and super-resolution, demonstrate that the proposed deep network can achieve superior performance against state-of-the-art model-based and learning-based methods.

In order to solve the problem that the traditional DV-Hop location algorithm has a large error in locating unknown nodes, this paper proposes an improved DV-Hop algorithm based on dual communication radius. By adding a communication radius, the algorithm updates the minimum hop number obtained by the unknown node closer to the beacon node to a smaller hop value and keeps the minimum hop number information of unknown nodes farther away. This method reflects the gap between the actual distances in terms of hop number, which solves the problem of the large difference between the actual distances of the same hops to a certain extent. Therefore, it is more advantageous to estimate the more accurate average jump distance and can calculate the more precise distance between them and obtain the more precise coordinates of unknown nodes. MATLAB simulation results show that the improved algorithm based on dual communication radius DV-Hop can effectively reduce the location error and improve the location accuracy and stability compared with the traditional DV-Hop location algorithm.

Depth maps have been widely used in many real world applications, such as human-computer interaction and virtual reality. However, due to the limitation of current depth sensing technology, the captured depth maps usually suffer from low resolution and insufficient quality. In this paper, we propose a depth map super-resolution method via joint local gradient and nonlocal structural regularizations. Depth maps contain mainly smooth areas separated by textures which demonstrate distinct geometry direction characteristic. Motivated by this, we classify depth map patches according to their geometrical directions and learn a compact online dictionary in each class. We further introduce two regularization terms into the sparse representation framework. Firstly, a multi-directional total variation model is proposed to characterize the local patterns in the gradient domain. Secondly, a nonlocal autoregressive model is introduced to provide nonlocal constraint to the local structures, which can effectively restore image details and suppress noise. Quantitative and qualitative evaluations compared with state-of-the-art methods demonstrate that the proposed method achieves superior performance for various configurations of magnification factors and datasets.