Super-Resolution via Wavelet Transform and Advanced Learning Techniques

Abstract

Image super-resolution aims to generate a high-resolution (HR) image from a low-resolution (LR) input image. In this paper, we propose a deep learning-based approach for image super-resolution. We use the wavelet transform to separate the input image into four frequency bands, and train a model for each sub-band. By processing information from different frequency bands via different CNN models, we can extract features more efficiently and learn better LR-to-HR mapping. In addition, we add dense connection to the model to make better use of the internal features in the CNN model. Furthermore, geometric self-ensemble is applied in the testing stage to maximize the potential performance. Extensive experiments on four benchmark datasets show the efficiency of the proposed method.