Automatic Search Dense Connection Module for Super-Resolution
Open Access
Abstract
The development of display technology has continuously increased the requirements for image resolution. However, the imaging systems of many cameras are limited by their physical conditions, and the image resolution is often restrictive. Recently, several models based on deep convolutional neural network (CNN) have gained significant performance for image super-resolution (SR), while extensive memory consumption and computation overhead hinder practical applications. For this purpose, we present a lightweight network that automatically searches dense connection (ASDCN) for image super-resolution (SR), which effectively reduces redundancy in dense connection and focuses on more valuable features. We employ neural architecture search (NAS) to model the searching of dense connections. Qualitative and quantitative experiments on five public datasets show that our derived model achieves superior performance over the state-of-the-art models.Keywords
Funding Information
- Anhui Science and Technology Department (No. JD2019XKJH0029;No. 2021008)
This publication has 35 references indexed in Scilit:
- NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study2017
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Image Super-Resolution via Deep Recursive Residual Network2017
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution2017
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Deep Residual Learning for Image Recognition2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004