Four-path unsupervised learning-based image defogging network
To solve the problems of supervised network and unsupervised network in the field of single image defogging, a four-path unsupervised learning-based image defogging network based on cycle generative adversarial network (CycleGAN) was proposed, which mainly included three sub-networks: defogging netw...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2022-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022201/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539965498949632 |
|---|---|
| author | Wei LIU Cheng CHEN Rui JIANG Tao LU |
| author_facet | Wei LIU Cheng CHEN Rui JIANG Tao LU |
| author_sort | Wei LIU |
| collection | DOAJ |
| description | To solve the problems of supervised network and unsupervised network in the field of single image defogging, a four-path unsupervised learning-based image defogging network based on cycle generative adversarial network (CycleGAN) was proposed, which mainly included three sub-networks: defogging network, synthetic fog network and attention feature fusion network.The three sub-networks were sequentially combined to construct four learning paths, which were the defogging path, the color-texture recovery path for defogged result, the synthetic fog path, and the color-texture recovery path for synthetic fog result.Specifically, in the synthetic fog network, to better constrain the defogging network to generate higher quality fogfree images, the atmospheric scattering model (ASM)was introduced to enhance the mapping transformation of the network from the foggy image domain to the fogfree image domain.Furthermore, to further improve the image generation quality of the defogging network and the synthetic fog network, an attention feature fusion network was proposed.The proposed network was based on several fog-derived images, which adopts a multi-channel mapping structure and an attention mechanism to enhance the recovery of color and texture details.Extensive experiments on both synthetic and real-world datasets show that the proposed method can better restore the color and texture details information of foggy images in various scenes. |
| format | Article |
| id | doaj-art-3e3448ae699d42df9bca096e0b179a64 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2022-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-3e3448ae699d42df9bca096e0b179a642025-01-14T06:30:08ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2022-10-014321022259396505Four-path unsupervised learning-based image defogging networkWei LIUCheng CHENRui JIANGTao LUTo solve the problems of supervised network and unsupervised network in the field of single image defogging, a four-path unsupervised learning-based image defogging network based on cycle generative adversarial network (CycleGAN) was proposed, which mainly included three sub-networks: defogging network, synthetic fog network and attention feature fusion network.The three sub-networks were sequentially combined to construct four learning paths, which were the defogging path, the color-texture recovery path for defogged result, the synthetic fog path, and the color-texture recovery path for synthetic fog result.Specifically, in the synthetic fog network, to better constrain the defogging network to generate higher quality fogfree images, the atmospheric scattering model (ASM)was introduced to enhance the mapping transformation of the network from the foggy image domain to the fogfree image domain.Furthermore, to further improve the image generation quality of the defogging network and the synthetic fog network, an attention feature fusion network was proposed.The proposed network was based on several fog-derived images, which adopts a multi-channel mapping structure and an attention mechanism to enhance the recovery of color and texture details.Extensive experiments on both synthetic and real-world datasets show that the proposed method can better restore the color and texture details information of foggy images in various scenes.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022201/cycle generative adversarial networksingle image defoggingatmospheric scattering modelattention feature fusionunsupervised learning |
| spellingShingle | Wei LIU Cheng CHEN Rui JIANG Tao LU Four-path unsupervised learning-based image defogging network Tongxin xuebao cycle generative adversarial network single image defogging atmospheric scattering model attention feature fusion unsupervised learning |
| title | Four-path unsupervised learning-based image defogging network |
| title_full | Four-path unsupervised learning-based image defogging network |
| title_fullStr | Four-path unsupervised learning-based image defogging network |
| title_full_unstemmed | Four-path unsupervised learning-based image defogging network |
| title_short | Four-path unsupervised learning-based image defogging network |
| title_sort | four path unsupervised learning based image defogging network |
| topic | cycle generative adversarial network single image defogging atmospheric scattering model attention feature fusion unsupervised learning |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022201/ |
| work_keys_str_mv | AT weiliu fourpathunsupervisedlearningbasedimagedefoggingnetwork AT chengchen fourpathunsupervisedlearningbasedimagedefoggingnetwork AT ruijiang fourpathunsupervisedlearningbasedimagedefoggingnetwork AT taolu fourpathunsupervisedlearningbasedimagedefoggingnetwork |