Next Article in Journal
Sub-Graph Regularization on Kernel Regression for Robust Semi-Supervised Dimensionality Reduction
Previous Article in Journal
Transfer Entropy between Communities in Complex Financial Networks
Open AccessArticle

A Novel Residual Dense Pyramid Network for Image Dehazing

by Shibai Yin 1,2,3,*, Yibin Wang 4 and Yee-Hong Yang 5
1
Department of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu 611130, China
2
Key Laboratory of Financial Intelligence and Financial Engineering of Sichuan Province, Southwestern University of Finance and Economics, Chengdu 611130, China
3
Collaborative Innovation Center for the Innovation and Regulation of Internet-Based Finance, Southwestern University of Finance and Economics, Chengdu 611130, China
4
Department of Engineering, Sichuan Normal University, Chengdu 610066, China
5
Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, Canada
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(11), 1123; https://doi.org/10.3390/e21111123
Received: 22 October 2019 / Revised: 10 November 2019 / Accepted: 12 November 2019 / Published: 15 November 2019
(This article belongs to the Section Signal and Data Analysis)
Recently, convolutional neural network (CNN) based on the encoder-decoder structure have been successfully applied to image dehazing. However, these CNN based dehazing methods have two limitations: First, these dehazing models are large in size with enormous parameters, which not only consumes much GPU memory, but also is hard to train from scratch. Second, these models, which ignore the structural information at different resolutions of intermediate layers, cannot capture informative texture and edge information for dehazing by stacking more layers. In this paper, we propose a light-weight end-to-end network named the residual dense pyramid network (RDPN) to address the above problems. To exploit the structural information at different resolutions of intermediate layers fully, a new residual dense pyramid (RDP) is proposed as a building block. By introducing a dense information fusion layer and the residual learning module, the RDP can maximize the information flow and extract local features. Furthermore, the RDP further learns the structural information from intermediate layers via a multiscale pyramid fusion mechanism. To reduce the number of network parameters and to ease the training process, we use one RDP in the encoder and two RDPs in the decoder, following a multilevel pyramid pooling layer for incorporating global context features before estimating the final result. The extensive experimental results on a synthetic dataset and real-world images demonstrate that the new RDPN achieves favourable performance compared with some state-of-the-art methods, e.g., the recent densely connected pyramid dehazing network, the all-in-one dehazing network, the enhanced pix2pix dehazing network, pixel-based alpha blending, artificial multi-exposure image fusions and the genetic programming estimator, in terms of accuracy, run time and number of parameters. To be specific, RDPN outperforms all of the above methods in terms of PSNR by at least 4.25 dB. The run time of the proposed method is 0.021 s, and the number of parameters is 1,534,799, only 6% of that used by the densely connected pyramid dehazing network. View Full-Text
Keywords: image dehazing; residual dense pyramid; encoder-decoder; convolutional neural network image dehazing; residual dense pyramid; encoder-decoder; convolutional neural network
Show Figures

Figure 1

MDPI and ACS Style

Yin, S.; Wang, Y.; Yang, Y.-H. A Novel Residual Dense Pyramid Network for Image Dehazing. Entropy 2019, 21, 1123.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop