{"type":"ScholarlyArticle","title":"Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction","authors":[{"name":"De Cheng","slug":"de-cheng","given":"De","family":"Cheng","affiliation":"Xidian University"},{"name":"Yan Li","slug":"yan-li","given":"Yan","family":"Li","affiliation":"Shandong Normal University"},{"name":"Dingwen Zhang","slug":"dingwen-zhang","given":"Dingwen","family":"Zhang","affiliation":"Northwestern Polytechnical University; Institute of Artificial Intelligence , Hefei Comprehensive National Science Center"},{"name":"Nannan Wang","slug":"nannan-wang","given":"Nannan","family":"Wang","affiliation":"Xidian University"},{"name":"Xinbo Gao","slug":"xinbo-gao","given":"Xinbo","family":"Gao","affiliation":"Chongqing University of Posts and Telecommunications"},{"name":"Jiande Sun","slug":"jiande-sun","given":"Jiande","family":"Sun","affiliation":"Shandong Normal University"}],"abstract":"Single image dehazing as a fundamental low-level vision task, is essential for the development of robust intelligent surveillance system. In this paper, we make an early effort to consider dehazing robustness under variational haze density, which is a realistic while under-studied problem in the research filed of singe image dehazing. To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios. Specifically, the dehazing network is optimized under the consistency-regularized framework with the proposed Contrast-Assisted Reconstruction Loss (CARL). The CARL can fully exploit the negative information to facilitate the traditional positive-orient dehazing objective function, by squeezing the dehazed image to its clean target from different directions. Meanwhile, the consistency regularization keeps consistent outputs given multi-level hazy images, thus improving the model robustness. Extensive experimental results on two synthetic and  three real-world datasets demonstrate that our method significantly surpasses the state-of-the-art approaches.","doi":"10.24963/ijcai.2022/119","url":"https://ijcai.org/proceedings/2022/119","pdf":"https://ijcai.org/proceedings/2022/0119.pdf","markdown":"https://ijcai.org/proceedings/2022/119.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/119","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Computer Vision","track":"Main Track","number":119,"pages":{"first":848,"last":854},"keywords":["Computer Vision: Machine Learning for Vision","Computer Vision: Visual reasoning and symbolic representation","Computer Vision: Recognition (object detection, categorization)","Computer Vision: Structural and Model-Based Approaches, Knowledge Representation and Reasoning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986519","length_sec":84,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984662","length_sec":312,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Ancuti et al., 2018a] Codruta O Ancuti, Cosmin Ancuti, Radu Timofte, and Christophe De Vleeschouwer. O-haze: a dehazing benchmark with real hazy and haze-free out- door images. In CVPRW, 2018.","title":"and Christophe De Vleeschouwer. O-haze: a dehazing benchmark with real hazy and haze-free outdoor images","authors":"Ancuti","year":"2018","venue":"CVPRW","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ancuti et al., 2018b] Cosmin Ancuti, Codruta O Ancuti, Radu Timofte, and Christophe De Vleeschouwer. I-haze: a dehazing benchmark with real hazy and haze-free indoor images. In ACIVS, 2018.","title":"Cosmin Ancuti, Codruta O Ancuti, Radu Timofte, and Christophe De Vleeschouwer. I-haze: a dehazing benchmark with real hazy and haze-free indoor images","authors":"Ancuti","year":"2018","venue":"ACIVS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ancuti et al., 2019] Codruta O Ancuti, Cosmin Ancuti, Ma- teu Sbert, and Radu Timofte. Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images. In ICIP, 2019.","title":"Codruta O Ancuti, Cosmin Ancuti, Mateu Sbert, and Radu Timofte. Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images","authors":"Ancuti","year":"2019","venue":"ICIP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Berman et al., 2016] Dana Berman, Shai Avidan, et al. Non-local image dehazing. In CVPR, 2016.","title":"Non-local image dehazing","authors":"Dana Berman, Shai Avidan","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"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. IEEE TIP, 2016.","title":"Dehazenet: An end-to-end system for single image haze removal","authors":"Cai","year":"2016","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong et al., 2020a] Hang Dong, Jinshan Pan, Lei Xiang, Zhe Hu, Xinyi Zhang, Fei Wang, and Ming-Hsuan Yang. Multi-scale boosted dehazing network with dense feature fusion. In CVPR, 2020.","title":"Multi-scale boosted dehazing network with dense feature fusion","authors":"Dong","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dong et al., 2020b] Yu Dong, Yihao Liu, He Zhang, Shifeng Chen, and Yu Qiao. Fd-gan: Generative adver- sarial networks with fusion-discriminator for single image dehazing. In AAAI, 2020.","title":"Fd-gan: Generative adversarial networks with fusion-discriminator for single image dehazing","authors":"Dong","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2010] Kaiming He, Jian Sun, and Xiaoou Tang. Single image haze removal using dark channel prior. TPA- MI, 2010.","title":"Single image haze removal using dark channel prior","authors":"Kaiming He, Jian Sun, Xiaoou Tang","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[He et al., 2019] Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. Bag of trick- s for image classification with convolutional neural net- works. In CVPR, 2019.","title":"Bag of tricks for image classification with convolutional neural networks","authors":"Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hong et al., 2020] Ming Hong, Yuan Xie, Cuihua Li, and Yanyun Qu. Distilling image dehazing with heterogeneous task imitation. In CVPR, 2020.","title":"Distilling image dehazing with heterogeneous task imitation","authors":"Ming Hong, Yuan Xie, Cuihua Li, Yanyun Qu","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Johnson et al., 2016] Justin Johnson, Alexandre Alahi, and Li Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In ECCV, 2016.","title":"Perceptual losses for real-time style transfer and super-resolution","authors":"Justin Johnson, Alexandre Alahi, Li Fei-Fei","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ju et al., 2021] Mingye Ju, Can Ding, Charles A Guo, Wen- qi Ren, and Dacheng Tao. Idrlp: Image dehazing using region line prior. IEEE TIP, 2021.","title":"Idrlp: Image dehazing using region line prior","authors":"Ju","year":"2021","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Khosla et al., 2020] Prannay Khosla, Piotr Teterwak, and etal Wang. Supervised contrastive learning. arX- iv:2004.11362, 2020.","title":"Supervised contrastive learning","authors":"Khosla","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"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, 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":15,"raw":"[Li et al., 2018a] Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, and Dan Feng. End-to-end united video de- hazing and detection. In AAAI, 2018.","title":"End-to-end united video dehazing and detection","authors":"Li","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2018b] Boyi Li, Wenqi Ren, Dacheng Tao, Wenjun Zeng, and Zhangyang Wang. Benchmarking single-image dehazing and beyond. IEEE TIP, 2018.","title":"Benchmarking single-image dehazing and beyond","authors":"Li","year":"2018","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2020] Pengyue Li, Jiandong Tian, Yandong Tang, Guolin Wang, and Chengdong Wu. Deep retinex network for single image dehazing. IEEE TIP, 2020.","title":"Deep retinex network for single image dehazing","authors":"Li","year":"2020","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2019a] Xiaohong Liu, Yongrui Ma, Zhihao Shi, and Jun Chen. Griddehazenet: Attention-based multi-scale network for image dehazing. In ICCV, 2019.","title":"Griddehazenet: Attention-based multi-scale network for image dehazing","authors":"Liu","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2019b] Xing Liu, Masanori Suganuma, Zhun Sun, and Takayuki Okatani. Dual residual networks lever- aging the potential of paired operations for image restora- tion. In CVPR, 2019.","title":"Dual residual networks leveraging the potential of paired operations for image restoration","authors":"Liu","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Qin et al., 2020] Xu Qin, Zhilin Wang, Yuanchao Bai, X- iaodong Xie, and Huizhu Jia. Ffa-net: Feature fusion at- tention network for single image dehazing. In AAAI, 2020.","title":"Ffa-net: Feature fusion attention network for single image dehazing","authors":"Zhilin Xu Qin, Yuanchao Wang, Xiaodong Bai, Huizhu Xie, Jia","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qu et al., 2019] Yanyun Qu, Yizi Chen, Jingying Huang, and Yuan Xie. Enhanced pix2pix dehazing network. In CVPR, 2019.","title":"Enhanced pix2pix dehazing network","authors":"Qu","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":22,"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, 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":23,"raw":"[Ren et al., 2018] Wenqi Ren, Lin Ma, Xiaochun Cao, Wei Liu, and Ming-Hsuan Yang. Gated fusion network for sin- gle image dehazing. In CVPR, 2018.","title":"Gated fusion network for single image dehazing","authors":"Wenqi Ren, Lin Ma, Xiaochun Cao, Wei Liu, Ming-Hsuan Yang","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sakaridis et al., 2018] Christos Sakaridis, Dengxin Dai, and Luc Van Gool. Semantic foggy scene understanding with synthetic data. IJCV, 2018.","title":"Semantic foggy scene understanding with synthetic data","authors":"Christos Sakaridis, Dengxin Dai, Luc Van Gool","year":"2018","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shao et al., 2020] Yuanjie Shao, Lerenhan Li, Wenqi Ren, Changxin Gao, and Nong Sang. Domain adaptation for image dehazing. In CVPR, 2020.","title":"Domain adaptation for image dehazing","authors":"Shao","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tan, 2008] Robby T Tan. Visibility in bad weather from a single image. In CVPR, 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":28,"raw":"[Tarvainen and Valpola, 2017] Antti Tarvainen and Harri Valpola. Mean teachers are better role models: Weight- averaged consistency targets improve semi-supervised deep learning results. NeurIPS, 2017.","title":"Mean teachers are better role models: Weightaveraged consistency targets improve semi-supervised deep learning results","authors":"Valpola Tarvainen, Antti Tarvainen, Harri Valpola","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wu et al., 2021] Haiyan Wu, Yanyun Qu, Shaohui Lin, Jian Zhou, Ruizhi Qiao, Zhizhong Zhang, Yuan Xie, and L- izhuang Ma. Contrastive learning for compact single im- age dehazing. In CVPR, 2021.","title":"Contrastive learning for compact single image dehazing","authors":"Haiyan Wu, Yanyun Qu, Shaohui Lin, Jian Zhou, Ruizhi Qiao, Zhizhong Zhang, Yuan Xie, Lizhuang Ma","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yoon et al., 2021] Kuk-Jin Yoon, Pranjay Shyam, and Kyung-Soo Kim. Towards domain invariant single image dehazing. In AAAI, 2021.","title":"Towards domain invariant single image dehazing","authors":"Kuk-Jin Yoon, Pranjay Shyam, Kyung-Soo Kim","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang and Patel, 2018] He Zhang and Vishal Patel. Densely connected pyramid dehazing network. In CVPR, 2018.","title":"Densely connected pyramid dehazing network","authors":"Patel ; He Zhang, Vishal Zhang, Patel","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang et al., 2021a] Dingwen Zhang, Junwei Han, Gong Cheng, and Ming-Hsuan Yang. Weakly supervised object localization and detection: A survey. IEEE TPAMI, 2021.","title":"Weakly supervised object localization and detection: A survey","authors":"Zhang","year":"2021","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang et al., 2021b] Dingwen Zhang, Wenyuan Zeng, Jieru Yao, and Junwei Han. Weakly supervised object detection using proposal-and semantic-level relationships. IEEE T- PAMI, 2021.","title":"Weakly supervised object detection using proposal-and semantic-level relationships","authors":"Zhang","year":"2021","venue":"IEEE T-PAMI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}