Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network

TL;DR

This paper introduces a multi-scale CNN model for single image super-resolution that can handle multiple up-scale factors with a single trained model, improving flexibility and efficiency.

Contribution

The proposed MSSR network employs multi-scale paths for better feature synthesis and supports multiple up-scale factors with one model, unlike previous methods.

Findings

Achieved state-of-the-art performance on four datasets.

Demonstrated faster processing speed.

Effectively reconstructs various regions in HR images.

Abstract

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.