{"type":"ScholarlyArticle","title":"Dual-Path in Dual-Path Network for Single Image Dehazing","authors":[{"name":"Aiping Yang","slug":"aiping-yang","given":"Aiping","family":"Yang","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Haixin Wang","slug":"haixin-wang","given":"Haixin","family":"Wang","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Zhong Ji","slug":"zhong-ji","given":"Zhong","family":"Ji","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Yanwei Pang","slug":"yanwei-pang","given":"Yanwei","family":"Pang","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Ling Shao","slug":"ling-shao","given":"Ling","family":"Shao","affiliation":"School of Electrical and Information Engineering , Tianjin University , China; Inception Institute of Articial Intelligence , Abu Dhabi , UAE"}],"abstract":"Recently, deep learning-based single image dehazing method has been a popular approach to tackle dehazing. However, the existing dehazing approaches are performed directly on the original hazy image, which easily results in image blurring and noise amplifying. To address this issue, the paper proposes a DPDP-Net (Dual-Path in Dual-Path network) framework by employing a hierarchical dual path network. Specifically, the first-level dual-path network consists of a Dehazing Network and a Denoising Network, where the Dehazing Network is responsible for haze removal in the structural layer, and the Denoising Network deals with noise in the textural layer, respectively. And the second-level dual-path network lies in the Dehazing Network, which has an AL-Net (Atmospheric Light Network) and a TM-Net (Transmission Map Network), respectively. Concretely, the AL-Net aims to train the non-uniform atmospheric light, while the TM-Net aims to train the transmission map that reflects the visibility of the image. The final dehazing image is obtained by nonlinearly fusing the output of the Denoising Network and the Dehazing Network. Extensive experiments demonstrate that our proposed DPDP-Net achieves competitive performance against the state-of-the-art methods on both synthetic and real-world images.","doi":"10.24963/ijcai.2019/643","url":"https://ijcai.org/proceedings/2019/643","pdf":"https://ijcai.org/proceedings/2019/0643.pdf","markdown":"https://ijcai.org/proceedings/2019/643.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/643","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning Applications","track":"Main track","number":643,"pages":{"first":4627,"last":4634},"keywords":["Computer Vision: Computer Vision","Machine Learning Applications: Applications of Supervised Learning"],"videos":[],"references":[{"position":1,"raw":"[Ancuti et al., 2016] Cosmin Ancuti, Codruta O. Ancuti, and Christophe De Vleeschouwer. D-hazy: A dataset to eval- uate quantitatively dehazing algorithms. In ICIP, pages 2226-2230, 2016.","title":"D-hazy: A dataset to evaluate quantitatively dehazing algorithms","authors":"Cosmin Ancuti, Codruta O Ancuti, Christophe De Vleeschouwer","year":"2016","venue":"ICIP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berman et al., 2016] Dana Berman, Tali Treibitz, and Shai Avidan. Non-local image dehazing. In CVPR, pages 1674- 1682, 2016.","title":"Non-local image dehazing","authors":"Dana Berman, Tali Treibitz, Shai Avidan","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai et al., 2016] Bolun Cai, Xiangmin Xu, Kui Jia, Chun- mei Qing, and Dacheng Tao. Dehazenet: An end-to-end system for single image haze removal. TIP, 25(11):5187- 5198, 2016.","title":"Dehazenet: An end-to-end system for single image haze removal","authors":"Cai","year":"2016","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li Jia Li, Kai Li, and Fei Fei Li. Imagenet: a large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: a large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li Jia Li, Kai Li, Fei Fei, Li","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[He et al., 2009] Kaiming He, Jian Sun, and Xiaoou Tang. Single image haze removal using dark channel prior. In CVPR, pages 1956-1963, 2009.","title":"Single image haze removal using dark channel prior","authors":"Kaiming He, Jian Sun, Xiaoou Tang","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[He et al., 2010] Kaiming He, Sun Jian, and Xiaoou Tang. Guided image filtering. In ECCV, 2010.","title":"Guided image filtering","authors":"Kaiming He, Sun Jian, Xiaoou Tang","year":"2010","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lai et al., 2015] Yi Hsuan Lai, YiLei Chen, Chuan Ju Chiou, and Chiou Ting Hsu. Single image dehazing vi- a optimal transmission map under scene priors. TCSVT, 25(1):1-14, 2015.","title":"Single image dehazing via optimal transmission map under scene priors","authors":"Lai Yi Hsuan, Yilei Chen, Chuan Ju Chiou, Chiou Ting Hsu","year":"2015","venue":"TCSVT","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2014] Yu Li, Fangfang Guo, Robby T. Tan, and Michael S. Brown. A contrast enhancement framework with jpeg artifacts suppression. In ECCV, pages 174-188, 2014.","title":"A contrast enhancement framework with jpeg artifacts suppression","authors":"Yu Li, Fangfang Guo, Robby T Tan, Michael S Brown","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Li et al., 2017] Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, and Dan Feng. Aod-net: All-in-one dehaz- ing network. In ICCV, pages 4780-4788, 2017.","title":"Aod-net: All-in-one dehazing network","authors":"Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2019] Boyi Li, Wenqi Ren, Dengpan Fu, Dacheng Tao, Dan Feng, Wenjun Zeng, and Zhangyang Wang. Benchmarking single-image dehazing and beyond. TIP, 28(1):492-505, 2019.","title":"Benchmarking single-image dehazing and beyond","authors":"Boyi Li, Wenqi Ren, Dengpan Fu, Dacheng Tao, Dan Feng, Wenjun Zeng, Zhangyang Wang","year":"2019","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu and Zhao, 2018] Yu Liu and Guanlong Zhao. Pad-net: A perception-aided single image dehazing network. CoRR, abs/1805.03146, 2018.","title":"Pad-net: A perception-aided single image dehazing network","authors":"Yu Liu, Guanlong Zhao","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2015] Fayao Liu, Chunhua Shen, and Guosheng Lin. Deep convolutional neural fields for depth estimation from a single image. In CVPR, pages 5162-5170, 2015.","title":"Deep convolutional neural fields for depth estimation from a single image","authors":"Liu","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2018] Zheng Liu, Botao Xiao, Muhammad Alrabeiah, Keyan Wang, and Jun Chen. Generic model- agnostic convolutional neural network for single image de- hazing. CoRR, abs/1810.02862, 2018.","title":"Generic modelagnostic convolutional neural network for single image dehazing","authors":"Zheng Liu, Botao Xiao, Muhammad Alrabeiah, Keyan Wang, Jun Chen","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Meng et al., 2014] Gaofeng Meng, Ying Wang, Jiangyong Duan, Shiming Xiang, and Chunhong Pan. Efficient image dehazing with boundary constraint and contextual regular- ization. In ICCV, pages 617-624, 2014.","title":"Efficient image dehazing with boundary constraint and contextual regularization","authors":"Gaofeng Meng, Ying Wang, Jiangyong Duan, Shiming Xiang, Chunhong Pan","year":"2014","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Narasimhan and Nayar, 2002] Srinivasa G. Narasimhan and Shree K. Nayar. Vision and the atmosphere. IJCV, 48(3):233-254, 2002.","title":"Vision and the atmosphere","authors":"G Srinivasa, Shree K Narasimhan, Nayar","year":"2002","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Narasimhan and Nayar, 2003] S. G. Narasimhan and S. K. Nayar. Contrast restoration of weather degraded images. TPAMI, 25(6):713-724, 2003.","title":"Contrast restoration of weather degraded images","authors":"S G Narasimhan, S K Nayar","year":"2003","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nayar, 1999] Shree K. Nayar. Vision in bad weather. ICCV, 1999.","title":"Vision in bad weather. ICCV","authors":"K Shree, Nayar","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Qingsong et al., 2015] Zhu Qingsong, Mai Jiaming, and Shao Ling. A fast single image haze removal algorith- m using color attenuation prior. TIP, 24(11):3522-3533, 2015.","title":"A fast single image haze removal algorithm using color attenuation prior","authors":"Zhu Qingsong, Mai Jiaming, Shao Ling","year":"2015","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ren et al., 2016] Wenqi Ren, Si Liu, Hua Zhang, Jinshan Pan, Xiaochun Cao, and Ming-Hsuan Yang. Single image dehazing via multi-scale convolutional neural networks. In ECCV, pages 154-169, 2016.","title":"Single image dehazing via multi-scale convolutional neural networks","authors":"Si Wenqi Ren, Hua Liu, Jinshan Zhang, Xiaochun Pan, Ming-Hsuan Cao, Yang","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ren et al., 2018] Wenqi Ren, Lin Ma, Jiawei Zhang, Jin- shan Pan, Xiaochun Cao, Wei Liu, and Ming-Hsuan Yang. Gated fusion network for single image dehazing. In CVPR, 2018.","title":"Gated fusion network for single image dehazing","authors":"Wenqi Ren, Lin Ma, Jiawei Zhang, Jinshan Pan, Xiaochun Cao, Wei Liu, Ming-Hsuan Yang","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Scharstein and Pal, 2007] D. Scharstein and C. Pal. Learn- ing conditional random fields for stereo. In CVPR, pages 1-8, 2007.","title":"Learning conditional random fields for stereo","authors":"D Scharstein, C","year":"2007","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Scharstein and Szeliski, 2003] D. Scharstein and R. Szelis- ki. High-accuracy stereo depth maps using structured light. In CVPR, pages 195-202, 2003.","title":"High-accuracy stereo depth maps using structured light","authors":"D Scharstein, R Szeliski","year":"2003","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Silberman et al., 2012] Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. Indoor segmentation and support inference from rgbd images. In ECCV, pages 746-760, 2012.","title":"Indoor segmentation and support inference from rgbd images","authors":"Nathan Silberman, Derek Hoiem, Pushmeet Kohli, Rob Fergus","year":"2012","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tan, 2008] Robby T. Tan. Visibility in bad weather from a single image. In CVPR, pages 1-8, 2008.","title":"Visibility in bad weather from a single image","authors":"Robby T Tan","year":"2008","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2019] A. Wang, W. Wang, J. Liu, and N. Gu. Aipnet: Image-to-image single image dehazing with at- mospheric illumination prior. TIP, 28(1):381-393, 2019.","title":"Aipnet: Image-to-image single image dehazing with atmospheric illumination prior","authors":"A Wang, W Wang, J Liu, N Gu","year":"2019","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xi et al., 2018] Zhao Xi, Keyan Wang, Yunsong Li, and Jiaojiao Li. Deep fully convolutional regression networks for single image haze removal. In VCIP, 2018.","title":"Deep fully convolutional regression networks for single image haze removal","authors":"Zhao Xi, Keyan Wang, Yunsong Li, Jiaojiao Li","year":"2018","venue":"VCIP","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xiaogang et al., 2014] Wang Xiaogang, Wang Meng, and Li Wei. Scene-specific pedestrian detection for static video surveillance. TPAMI, 36(2):361-374, 2014.","title":"Scene-specific pedestrian detection for static video surveillance","authors":"Wang Xiaogang, Wang Meng, Li Wei","year":"2014","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yang et al., 2017] Hui Yang, Jinshan Pan, Qiong Yan, Wenxiu Sun, Jimmy S. J. Ren, and Yu-Wing Tai. Image dehazing using bilinear composition loss function. CoRR, abs/1710.00279, 2017.","title":"Image dehazing using bilinear composition loss function","authors":"Hui Yang, Jinshan Pan, Qiong Yan, Wenxiu Sun, Jimmy S J Ren, Yu-Wing Tai","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang and Patel, 2018] H. Zhang and V. M. Patel. Dense- ly connected pyramid dehazing network. In CVPR, pages 3194-3203, 2018.","title":"Densely connected pyramid dehazing network","authors":"H Zhang, V M Patel","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2011] Lin Zhang, Lei Zhang, Xuanqin Mou, and David Zhang. Fsim: A feature similarity index for image quality assessment. TIP, pages 2378 -2386, 2011.","title":"Fsim: A feature similarity index for image quality assessment","authors":"Lin Zhang, Lei Zhang, Xuanqin Mou, David Zhang","year":"2011","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang et al., 2017] Kai Zhang, Wangmeng Zuo, and Lei Zhang. Ffdnet: Toward a fast and flexible solution for cnn based image denoising. TIP, 2017.","title":"Ffdnet: Toward a fast and flexible solution for cnn based image denoising","authors":"Kai Zhang, Wangmeng Zuo, Lei Zhang","year":"2017","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zheng et al., 2012] W. S. Zheng, S. Gong, and T. Xiang. Quantifying and transferring contextual information in ob- ject detection. TPAMI, 34(4):762-777, 2012.","title":"Quantifying and transferring contextual information in object detection","authors":"W S Zheng, S Gong, T Xiang","year":"2012","venue":"TPAMI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}