RBDN: Residual Bottleneck Dense Network for Image Super-Resolution
Authors:
Open Access
- 12 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 103440-103451
Abstract
Recent studies have shown that a super-resolution generative adversarial network (SRGAN) can significantly improve the quality of single-image super-resolution. However, existing SRGAN methods also have certain drawbacks, such as an insufficient feature utilization, a large number of parameters. To further enhance the visual quality, we thoroughly studied three key components of SRGAN, i.e., the network architecture, adversarial loss, and perceptual loss, and propose a DenseNet with Residual-in-Residual Bottleneck Block (RRBB), called a residual bottleneck dense network (RBDN), for single-image super-resolution. First, to improve the utilization of features between the various layers of the network, we adopted a dense cascading connection between layers. At the same time, to reduce the computational cost, we added a bottleneck structure to each layer, greatly reducing the number of network parameters and accelerating the convergence speed of the training process. Second, the proposed RRBB, as the basic network building unit, removes the batch normalization (BN) layer and employs the ELU function to reduce the opposite effects in the absence of BN. In addition, we applied an improved overall loss function during the model training process to stably train the model and further improve the realism of the reconstructed high-resolution image. To prove the superiority of our proposed model, we conducted a comprehensive and objective evaluation of the Peak Signal-to-Noise Ratio, structural similarity, learned perceptual image patch similarity, and other evaluation indicators obtained from the three test sets, i.e., Set5, Set14, and BSD100, from the recent state-of-the-art model. Finally, we conducted qualitative and quantitative analyses of the results obtained in terms of the evaluation indicators, the authenticity of the restored HR images, and textural details, which show the superiority of the RBDN model.Keywords
All Related Versions
Funding Information
- Natural Science Foundation of Chongqing Municipality (cstc2020jcyj-msxmX0057)
- Fundamental Research Funds for the Central Universities (XDJK2018B013)
This publication has 33 references indexed in Scilit:
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image RestorationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Deep Residual Learning for Image Recognition2016
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- Wide Residual Networks2016
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Proximal AlgorithmsFoundations and Trends® in Optimization, 2014
- Learning a Deep Convolutional Network for Image Super-Resolution2014
- On Single Image Scale-Up Using Sparse-Representations2012
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002