An Enhanced pix2pix Dehazing Network with Guided Filter Layer
In this paper, we propose an enhanced pix2pix dehazing network, which generates clear images without relying on a physical scattering model. This network is a generative adversarial network (GAN) which combines multiple guided filter layers. First, the input of hazy images is smoothed to obtain high...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/17/5898 |
| _version_ | 1827707542287941632 |
|---|---|
| author | Qirong Bu Jie Luo Kuan Ma Hongwei Feng Jun Feng |
| author_facet | Qirong Bu Jie Luo Kuan Ma Hongwei Feng Jun Feng |
| author_sort | Qirong Bu |
| collection | DOAJ |
| description | In this paper, we propose an enhanced pix2pix dehazing network, which generates clear images without relying on a physical scattering model. This network is a generative adversarial network (GAN) which combines multiple guided filter layers. First, the input of hazy images is smoothed to obtain high-frequency features according to different smoothing kernels of the guided filter layer. Then, these features are embedded in higher dimensions of the network and connected with the output of the generator’s encoder. Finally, Visual Geometry Group (VGG) features are introduced to serve as a loss function to improve the quality of the texture information restoration and generate better hazy-free images. We conduct experiments on NYU-Depth, I-HAZE and O-HAZE datasets. The enhanced pix2pix dehazing network we propose produces increases of 1.22 dB in the Peak Signal-to-Noise Ratio (PSNR) and 0.01 in the Structural Similarity Index Metric (SSIM) compared with a second successful comparison method using the indoor test dataset. Extensive experiments demonstrate that the proposed method has good performance for image dehazing. |
| first_indexed | 2024-03-10T16:49:03Z |
| format | Article |
| id | doaj.art-b544cfff646b4220a33566193c0fd706 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T16:49:03Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b544cfff646b4220a33566193c0fd7062023-11-20T11:22:45ZengMDPI AGApplied Sciences2076-34172020-08-011017589810.3390/app10175898An Enhanced pix2pix Dehazing Network with Guided Filter LayerQirong Bu0Jie Luo1Kuan Ma2Hongwei Feng3Jun Feng4School of Information Science and Technology, Northwest Univesity, Xi’an 710127, ChinaSchool of Information Science and Technology, Northwest Univesity, Xi’an 710127, ChinaSchool of Information Science and Technology, Northwest Univesity, Xi’an 710127, ChinaSchool of Information Science and Technology, Northwest Univesity, Xi’an 710127, ChinaSchool of Information Science and Technology, Northwest Univesity, Xi’an 710127, ChinaIn this paper, we propose an enhanced pix2pix dehazing network, which generates clear images without relying on a physical scattering model. This network is a generative adversarial network (GAN) which combines multiple guided filter layers. First, the input of hazy images is smoothed to obtain high-frequency features according to different smoothing kernels of the guided filter layer. Then, these features are embedded in higher dimensions of the network and connected with the output of the generator’s encoder. Finally, Visual Geometry Group (VGG) features are introduced to serve as a loss function to improve the quality of the texture information restoration and generate better hazy-free images. We conduct experiments on NYU-Depth, I-HAZE and O-HAZE datasets. The enhanced pix2pix dehazing network we propose produces increases of 1.22 dB in the Peak Signal-to-Noise Ratio (PSNR) and 0.01 in the Structural Similarity Index Metric (SSIM) compared with a second successful comparison method using the indoor test dataset. Extensive experiments demonstrate that the proposed method has good performance for image dehazing.https://www.mdpi.com/2076-3417/10/17/5898pix2pixguided filter layerVGG |
| spellingShingle | Qirong Bu Jie Luo Kuan Ma Hongwei Feng Jun Feng An Enhanced pix2pix Dehazing Network with Guided Filter Layer Applied Sciences pix2pix guided filter layer VGG |
| title | An Enhanced pix2pix Dehazing Network with Guided Filter Layer |
| title_full | An Enhanced pix2pix Dehazing Network with Guided Filter Layer |
| title_fullStr | An Enhanced pix2pix Dehazing Network with Guided Filter Layer |
| title_full_unstemmed | An Enhanced pix2pix Dehazing Network with Guided Filter Layer |
| title_short | An Enhanced pix2pix Dehazing Network with Guided Filter Layer |
| title_sort | enhanced pix2pix dehazing network with guided filter layer |
| topic | pix2pix guided filter layer VGG |
| url | https://www.mdpi.com/2076-3417/10/17/5898 |
| work_keys_str_mv | AT qirongbu anenhancedpix2pixdehazingnetworkwithguidedfilterlayer AT jieluo anenhancedpix2pixdehazingnetworkwithguidedfilterlayer AT kuanma anenhancedpix2pixdehazingnetworkwithguidedfilterlayer AT hongweifeng anenhancedpix2pixdehazingnetworkwithguidedfilterlayer AT junfeng anenhancedpix2pixdehazingnetworkwithguidedfilterlayer AT qirongbu enhancedpix2pixdehazingnetworkwithguidedfilterlayer AT jieluo enhancedpix2pixdehazingnetworkwithguidedfilterlayer AT kuanma enhancedpix2pixdehazingnetworkwithguidedfilterlayer AT hongweifeng enhancedpix2pixdehazingnetworkwithguidedfilterlayer AT junfeng enhancedpix2pixdehazingnetworkwithguidedfilterlayer |