Yun Liang
ABSTRACT
Nighttime image dehazing is critical for many computer applications. Directly transferring daytime dehazing models to nighttime scenes often introduces haze residual, detail loss and color distortion for the uneven distribution by artificial lights. Therefore, we propose a nighttime dehazing method by defining the Dual-domain Feature Learning Module (DFLM) and the Feature Optimization Module (FOM). Firstly, we construct the DFLM in both frequency and spatial domains to accurately predict the image degradation caused by haze and remove most haze in nighttime hazy images. Secondly, to address the challenges of uneven illumination distribution and color interference of light sources in nighttime, we construct the FOM based on the proposed Cross Dimension Interaction Attention (CDIA), which captures the feature dependencies by crossing different dimensions including the channel-channel, height-channel and width-channel. By precisely representing illumination and color features, the FOM alleviates color distortion in nighttime dehazing. Extensive experiments on several synthetic and real-world datasets demonstrate that our method outperforms most state-of-the-art methods. Code will be available.
- Harshan Baskar, Anirudh S Chakravarthy, Prateek Garg, Divyam Goel, Abhijith S Raj, Kshitij Kumar, Ravichandra Parvatham, V Sushant, Bijay Kumar Rout, 2022. Nighttime Dehaze-Enhancement. arXiv preprint arXiv:2210.09962 (2022).Google Scholar
- Dana Berman, Tali Treibitz, and Shai Avidan. 2018. Single image dehazing using haze-lines. IEEE transactions on pattern analysis and machine intelligence 42, 3 (2018), 720–734.Google Scholar
- Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, and Dacheng Tao. 2016. Dehazenet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing 25, 11 (2016), 5187–5198.Google ScholarDigital Library
- Yue Cao, Jiarui Xu, Stephen Lin, Fangyun Wei, and Han Hu. 2019. Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In Proceedings of the IEEE/CVF international conference on computer vision workshops. 0–0.Google ScholarCross Ref
- Hang Dong, Jinshan Pan, Lei Xiang, Zhe Hu, Xinyi Zhang, Fei Wang, and Ming-Hsuan Yang. 2020. Multi-scale boosted dehazing network with dense feature fusion. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2157–2167.Google ScholarCross Ref
- Kaiming He, Jian Sun, and Xiaoou Tang. 2010. Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence 33, 12 (2010), 2341–2353.Google Scholar
- Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. 2019. Bag of tricks for image classification with convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 558–567.Google ScholarCross Ref
- Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7132–7141.Google ScholarCross Ref
- Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14. Springer, 694–711.Google ScholarCross Ref
- Manjit Kaur, Dilbag Singh, Vijay Kumar, and Kehui Sun. 2020. Color image dehazing using gradient channel prior and guided l0 filter. Information Sciences 521 (2020), 326–342.Google ScholarDigital Library
- Diederik P Kingma. 2014. A method for stochastic optimization. ArXiv Prepr (2014).Google Scholar
- Harald Koschmieder. 1924. Theorie der horizontalen Sichtweite. Beitrage zur Physik der freien Atmosphare (1924), 33–53.Google Scholar
- Shiba Kuanar, KR Rao, Dwarikanath Mahapatra, and Monalisa Bilas. 2019. Night time haze and glow removal using deep dilated convolutional network. arXiv preprint arXiv:1902.00855 (2019).Google Scholar
- Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, and Dan Feng. 2017. Aod-net: All-in-one dehazing network. In Proceedings of the IEEE international conference on computer vision. 4770–4778.Google ScholarCross Ref
- Jiafeng Li, Hong Zhang, Ding Yuan, and Mingui Sun. 2015. Single image dehazing using the change of detail prior. Neurocomputing 156 (2015), 1–11.Google ScholarDigital Library
- Pengyue Li, Jiandong Tian, Yandong Tang, Guolin Wang, and Chengdong Wu. 2020. Deep retinex network for single image dehazing. IEEE Transactions on Image Processing 30 (2020), 1100–1115.Google ScholarDigital Library
- Yu Li, Robby T Tan, and Michael S Brown. 2015. Nighttime haze removal with glow and multiple light colors. In Proceedings of the IEEE international conference on computer vision. 226–234.Google ScholarDigital Library
- Yinghong Liao, Zhuo Su, Xiangguo Liang, and Bin Qiu. 2018. Hdp-net: Haze density prediction network for nighttime dehazing. In Advances in Multimedia Information Processing–PCM 2018: 19th Pacific-Rim Conference on Multimedia, Hefei, China, September 21-22, 2018, Proceedings, Part I. Springer, 469–480.Google Scholar
- Salma Abdel Magid, Yulun Zhang, Donglai Wei, Won-Dong Jang, Zudi Lin, Yun Fu, and Hanspeter Pfister. 2021. Dynamic high-pass filtering and multi-spectral attention for image super-resolution. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 4288–4297.Google ScholarCross Ref
- Earl J McCartney. 1976. Optics of the atmosphere: scattering by molecules and particles. New York (1976).Google Scholar
- Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. 2012. Making a “completely blind” image quality analyzer. IEEE Signal processing letters 20, 3 (2012), 209–212.Google Scholar
- Volodymyr Mnih, Nicolas Heess, Alex Graves, 2014. Recurrent models of visual attention. Advances in neural information processing systems 27 (2014).Google Scholar
- Soo-Chang Pei and Tzu-Yen Lee. 2012. Nighttime haze removal using color transfer pre-processing and dark channel prior. In 2012 19th IEEE International conference on image processing. IEEE, 957–960.Google ScholarCross Ref
- Xu Qin, Zhilin Wang, Yuanchao Bai, Xiaodong Xie, and Huizhu Jia. 2020. FFA-Net: Feature fusion attention network for single image dehazing. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 11908–11915.Google ScholarCross Ref
- Zequn Qin, Pengyi Zhang, Fei Wu, and Xi Li. 2021. Fcanet: Frequency channel attention networks. In Proceedings of the IEEE/CVF international conference on computer vision. 783–792.Google ScholarCross Ref
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).Google Scholar
- Song Sun and Xinhua Guo. 2016. Image enhancement using bright channel prior. In 2016 International Conference on Industrial Informatics-Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII). IEEE, 83–86.Google ScholarCross Ref
- Hossein Talebi and Peyman Milanfar. 2018. NIMA: Neural image assessment. IEEE transactions on image processing 27, 8 (2018), 3998–4011.Google Scholar
- Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.Google ScholarDigital Library
- Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV). 3–19.Google ScholarDigital Library
- Rui-Qi Wu, Zheng-Peng Duan, Chun-Le Guo, Zhi Chai, and Chongyi Li. 2023. RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 22282–22291.Google ScholarCross Ref
- Zhifeng Xie, Sen Wang, Ke Xu, Zhizhong Zhang, Xin Tan, Yuan Xie, and Lizhuang Ma. 2023. Boosting Night-time Scene Parsing with Learnable Frequency. IEEE Transactions on Image Processing (2023).Google ScholarDigital Library
- XG Xu, P Yang, and YL Liu. 2017. Night image dehazing based on full-scale retinex algorithm [J]. Micro Electronics & Computer 34, 7 (2017), 132–136.Google Scholar
- Wending Yan, Robby T Tan, and Dengxin Dai. 2020. Nighttime defogging using high-low frequency decomposition and grayscale-color networks. In European Conference on Computer Vision. Springer, 473–488.Google ScholarDigital Library
- Jiazhi Yu, Jun Zhang, Biyuan Li, Xiaochang Ni, and Jianqiang Mei. 2023. Nighttime Image Dehazing based on Bright and Dark Channel Prior and Gaussian Mixture Model. In Proceedings of the 2023 6th International Conference on Image and Graphics Processing. 44–50.Google ScholarDigital Library
- He Zhang and Vishal M Patel. 2018. Densely connected pyramid dehazing network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3194–3203.Google ScholarCross Ref
- Jing Zhang, Yang Cao, Shuai Fang, Yu Kang, and Chang Wen Chen. 2017. Fast haze removal for nighttime image using maximum reflectance prior. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7418–7426.Google ScholarCross Ref
- Jing Zhang, Yang Cao, and Zengfu Wang. 2014. Nighttime haze removal based on a new imaging model. In 2014 IEEE International Conference on Image Processing (ICIP). IEEE, 4557–4561.Google ScholarCross Ref
- Jing Zhang, Yang Cao, Zheng-Jun Zha, and Dacheng Tao. 2020. Nighttime dehazing with a synthetic benchmark. In Proceedings of the 28th ACM international conference on multimedia. 2355–2363.Google ScholarDigital Library
- Dong Zhao, Jia Li, Hongyu Li, and Long Xu. 2021. Complementary feature enhanced network with vision transformer for image dehazing. arXiv preprint arXiv:2109.07100 (2021).Google Scholar
- Qingsong Zhu, Jiaming Mai, and Ling Shao. 2015. A fast single image haze removal algorithm using color attenuation prior. IEEE transactions on image processing 24, 11 (2015), 3522–3533.Google Scholar
Index Terms
- Dual-domain Feature Learning and Cross Dimension Interaction Attention for Nighttime Image Dehazing
Recommendations
A Visibility-Guided Fusion Framework for Fast Nighttime Image Dehazing
Pattern Recognition and Computer VisionAbstractDefogging is an important image enhancement and restoration technique that is widely used for various computer vision and computational photography applications. While the vast majority of currently available defogging methods work well for ...
Nighttime image Dehazing with modified models of color transfer and guided image filter
Taking into account of the illumination characteristics of nighttime imaging, a new method for nighttime image dehazing is proposed in this paper. In the first place, based on the color transfer theory, the illumination level of nighttime hazy image can ...
Dual-Scale Single Image Dehazing via Neural Augmentation
Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free images with high ...
Comments