Single-Image Super-Resolution Neural Network via Hybrid Multi-Scale Features
Open Access
- 19 February 2022
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 10 (4) , 653
Abstract
In this paper, we propose an end-to-end single-image super-resolution neural network by leveraging hybrid multi-scale features of images. Different from most existing convolutional neural network (CNN) based solutions, our proposed network depends on the observation that image features extracted by CNN contain hybrid multi-scale features: both multi-scale local texture features and global structural features. By effectively exploiting these multi-scale and local-global features, our network involves far fewer parameters, leading to a large decrease in memory usage and computation during inference. Our network benefits from three key modules: (1) an efficient and lightweight feature extraction module (EFblock); (2) a hybrid multi-scale feature enhancement module (HMblock); and (3) a reconstruction–restoration module (DRblock). Experiments on five popular benchmarks demonstrate that our super-resolution approach achieves better performance with fewer parameters and less memory consumption, compared to more than 20 SOTAs. In summary, we propose a novel multi-scale super-resolution neural network (HMSF), which is more lightweight, has fewer parameters, and requires less execution time, but has better performance than the state-of-the-art methods. Compared to SOTAs, this method is more practical and better suited to run on constrained devices, such as PCs and mobile devices, without the need for a high-performance server.Keywords
This publication has 58 references indexed in Scilit:
- A Deep Convolutional Neural Network with Selection Units for Super-Resolution2017
- NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study2017
- Image Super-Resolution via Deep Recursive Residual Network2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- Accelerating the Super-Resolution Convolutional Neural Network2016
- Rethinking the Inception Architecture for Computer Vision2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Fast Direct Super-Resolution by Simple Functions2013
- Image Super-Resolution Via Sparse RepresentationIEEE Transactions on Image Processing, 2010