Feature-guided dictionary learning for patch-and-group sparse representations in single image deraining

Abstract

Single image deraining as a fundamental task in computer vision is important in improving the visual quality of images and videos. In this paper, we propose a feature-guided dictionary learning method for patch-and-group sparse representation in single image deraining. Specifically, we develop an external dictionary that learns the generic feature representation from a lot of natural images using Gaussian mixture models (GMMs), and a novel strategy is designed to learn an internal dictionary using the given rainy image guiding by the generic features. The external dictionary and the internal dictionary are adaptively tailored to produce a coherent dictionary, which can extend the representation abilities of the learned dictionary for the group-based sparse representation. Moreover, we present a novel patch-and-group sparse representation framework to reconstruct an image tending to be free of rain by simultaneously combining the local sparsity and the nonlocal self-similarity property. This framework can integrate their advantages of the two representative methods capable of capturing more effective features for the single image deraining. The results of experiments on both the synthetic and the real-world rainy images demonstrate that the proposed method delivers more favorable visual effects and superior quality results, and it outperforms several other state-of-the-art methods.