Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network
This work addresses the need for more flexible and efficient super-resolution models for image processing applications, though it is incremental in improving upon existing CNN methods.
The paper tackled the problem of single image super-resolution by proposing a multi-scale CNN that can handle multiple up-scale factors with a single model, achieving state-of-the-art performance on four public datasets with fast speed.
Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which limits the flexibility of models to infer various scales of details for high resolution (HR) output. Moreover, most of them train a specific model for each up-scale factor. In this paper, we propose a multi-scale super resolution (MSSR) network. Our network consists of multi-scale paths to make the HR inference, which can learn to synthesize features from different scales. This property helps reconstruct various kinds of regions in HR images. In addition, only one single model is needed for multiple up-scale factors, which is more efficient without loss of restoration quality. Experiments on four public datasets demonstrate that the proposed method achieved state-of-the-art performance with fast speed.