A Fast and Efficient Super-Resolution Network Using Hierarchical Dense Residual Learning

In deep convolutional neural networks (DCNNs) for single image super-resolution (SISR), the dense and residual feature refinement helps to stabilize the training network and enriches the feature values. However, most SISR networks do not fully exploit the rich feature information in the hierarchical...

Full description

Saved in:
Bibliographic Details
Main Authors: Duong, Vinh Van, Huu, Thuc Nguyen, Yim, Jonghoon, Jeon, Byeungwoo
Format: Conference Proceeding
Language:English
Subjects:
Computational efficiency
Conferences
Convolutional neural networks
deep convolutional networks
hierarchical dense residual learning
Performance evaluation
Single image super-resolution
Superresolution
Task analysis
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In deep convolutional neural networks (DCNNs) for single image super-resolution (SISR), the dense and residual feature refinement helps to stabilize the training network and enriches the feature values. However, most SISR networks do not fully exploit the rich feature information in the hierarchical dense residual connections, thus achieving relatively low performance. Besides, in many cases, a large model is not feasible to deploy on mobile or embedded devices. By exploiting the hierarchical dense residual learning, this paper proposes a fast and efficient hierarchical dense residual network (HDRN) to solve these problems. Specifically, we develop a dense compact residual group (DCRG), consisting of several compact residual blocks (CRB), which helps to increase the reusable feature capability. Our experimental results confirm that the proposed HDRN achieves better trade-off between the performance and computational costs than those state-of-the-art lightweight SISR methods.
ISSN:2381-8549
DOI:10.1109/ICIP42928.2021.9506786