ABSTRACT
One of the hardest problems in computer vision is image dehazing. In the single picture dehazing job, the approaches based on pixel domain mapping and prior knowledge of physical models have achieved amazing results. Sadly, most deep dehazing algorithms now in use have limited generalization capabilities, which makes it challenging to apply them to data samples with foggy conditions that exhibit a wide range of variation. We suggest an Iterative-Refining Diffusion Model built on the U-Net architecture to solve the issue. We show that the suggested approach may be used to the dehazing problem. It is based on Denoising Diffusion Probabilistic Models (DDPM) [14] and the denoising score matching. An empirical data distribution is created from the conventional normal distribution by a sequence of repeated refining stages that are comparable to the Langevin dynamics process. The U-Net architecture [27], the model’s network architecture, is trained with dehazing targets to progressively eliminate different haze levels from the output. Extensive analyses demonstrate that the proposed model outperforms the state-of-the-art methods on multiple benchmarks.
- Cosmin Ancuti, Codruta O Ancuti, and Christophe De Vleeschouwer. 2016. D-hazy: A dataset to evaluate quantitatively dehazing algorithms. In 2016 IEEE international conference on image processing (ICIP). IEEE, 2226–2230.Google ScholarCross Ref
- Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb, and Christian Etmann. 2021. Conditional image generation with score-based diffusion models. arXiv preprint arXiv:2111.13606 (2021).Google Scholar
- Andrew Brock, Jeff Donahue, and Karen Simonyan. 2018. Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018).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 Scholar
- Dongdong Chen, Mingming He, Qingnan Fan, Jing Liao, Liheng Zhang, Dongdong Hou, Lu Yuan, and Gang Hua. 2019. Gated context aggregation network for image dehazing and deraining. In 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, 1375–1383.Google Scholar
- Nanxin Chen, Yu Zhang, Heiga Zen, Ron J Weiss, Mohammad Norouzi, and William Chan. 2020. Wavegrad: Estimating gradients for waveform generation. arXiv preprint arXiv:2009.00713 (2020).Google Scholar
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248–255.Google ScholarCross Ref
- Zijun Deng, Lei Zhu, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Qing Zhang, Jing Qin, and Pheng-Ann Heng. 2019. Deep multi-model fusion for single-image dehazing. In Proceedings of the IEEE/CVF international conference on computer vision. 2453–2462.Google ScholarCross Ref
- Patrick Esser, Robin Rombach, and Bjorn Ommer. 2021. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 12873–12883.Google ScholarCross Ref
- Raanan Fattal. 2014. Dehazing using color-lines. ACM transactions on graphics (TOG) 34, 1 (2014), 1–14.Google Scholar
- Yosef Gandelsman, Assaf Shocher, and Michal Irani. 2019. " Double-DIP": unsupervised image decomposition via coupled deep-image-priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11026–11035.Google ScholarCross Ref
- Alona Golts, Daniel Freedman, and Michael Elad. 2019. Unsupervised single image dehazing using dark channel prior loss. IEEE transactions on Image Processing 29 (2019), 2692–2701.Google Scholar
- Yuanbiao Gou, Boyun Li, Zitao Liu, Songfan Yang, and Xi Peng. 2020. Clearer: Multi-scale neural architecture search for image restoration. Advances in neural information processing systems 33 (2020), 17129–17140.Google Scholar
- Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840–6851.Google Scholar
- Jonathan Ho, Chitwan Saharia, William Chan, David J Fleet, Mohammad Norouzi, and Tim Salimans. 2022. Cascaded diffusion models for high fidelity image generation. The Journal of Machine Learning Research 23, 1 (2022), 2249–2281.Google ScholarDigital Library
- Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, and Jianzhuang Liu. 2021. Neighbor2neighbor: Self-supervised denoising from single noisy images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 14781–14790.Google ScholarCross Ref
- Tong-yao JIA, Li ZHUO, Jia-feng LI, and Jing ZHANG. 2023. Research Advances on Deep Learning Based Single Image Dehazing. ACTA ELECTONICA SINICA 51, 1 (2023), 231.Google Scholar
- Zhi Jin, Muhammad Zafar Iqbal, Dmytro Bobkov, Wenbin Zou, Xia Li, and Eckehard Steinbach. 2019. A flexible deep CNN framework for image restoration. IEEE Transactions on Multimedia 22, 4 (2019), 1055–1068.Google ScholarDigital Library
- Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).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
- Boyi Li, Wenqi Ren, Dengpan Fu, Dacheng Tao, Dan Feng, Wenjun Zeng, and Zhangyang Wang. 2018. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing 28, 1 (2018), 492–505.Google ScholarDigital Library
- Wanwan Li. 2021. Image Synthesis and Editing with Generative Adversarial Networks (GANs): A Review. In 2021 Fifth World Conference on Smart Trends in Systems Security and Sustainability (WorldS4). IEEE, 65–70.Google ScholarCross Ref
- Wei-An Lin, Haofu Liao, Cheng Peng, Xiaohang Sun, Jingdan Zhang, Jiebo Luo, Rama Chellappa, and Shaohua Kevin Zhou. 2019. Dudonet: Dual domain network for ct metal artifact reduction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10512–10521.Google ScholarCross Ref
- Xiaohong Liu, Yongrui Ma, Zhihao Shi, and Jun Chen. 2019. Griddehazenet: Attention-based multi-scale network for image dehazing. In Proceedings of the IEEE/CVF international conference on computer vision. 7314–7323.Google ScholarCross Ref
- Kangfu Mei, Aiwen Jiang, Juncheng Li, and Mingwen Wang. 2019. Progressive feature fusion network for realistic image dehazing. In Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part I 14. Springer, 203–215.Google Scholar
- 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
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234–241.Google Scholar
- Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J Fleet, and Mohammad Norouzi. 2022. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4713–4726.Google Scholar
- Daniel Scharstein, Heiko Hirschmüller, York Kitajima, Greg Krathwohl, Nera Nešić, Xi Wang, and Porter Westling. 2014. High-resolution stereo datasets with subpixel-accurate ground truth. In Pattern Recognition: 36th German Conference, GCPR 2014, Münster, Germany, September 2-5, 2014, Proceedings 36. Springer, 31–42.Google ScholarCross Ref
- Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus. 2012. Indoor segmentation and support inference from rgbd images. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V 12. Springer, 746–760.Google ScholarDigital Library
- Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems 32 (2019).Google Scholar
- Hu Yu, Jie Huang, Kaiwen Zheng, Man Zhou, and Feng Zhao. 2023. High-quality Image Dehazing with Diffusion Model. arXiv preprint arXiv:2308.11949 (2023).Google Scholar
- He Zhang, Vishwanath Sindagi, and Vishal M Patel. 2018. Multi-scale single image dehazing using perceptual pyramid deep network. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 902–911.Google ScholarCross Ref
- Shengdong Zhang, Fazhi He, and Wenqi Ren. 2020. NLDN: Non-local dehazing network for dense haze removal. Neurocomputing 410 (2020), 363–373.Google ScholarCross Ref
Index Terms
- Image Dehazing based on Iterative-Refining Diffusion Model
Recommendations
Single Image Dehazing via Image Generating
Image and Video TechnologyAbstractOutdoor images taken in bad weather conditions often suffer from poor visibility. However, single image haze removal is an ill-posed problem, because the number of the equations is smaller than the number of unknowns. In this paper, a deep ...
Photo-realistic dehazing via contextual generative adversarial networks
AbstractSingle image dehazing is a challenging task due to its ambiguous nature. In this paper we present a new model based on generative adversarial networks (GANs) for single image dehazing, called as dehazing GAN. In contrast to estimating the ...
Discrete Haze Level Dehazing Network
MM '20: Proceedings of the 28th ACM International Conference on MultimediaIn contrast to traditional dehazing methods, deep learning based single image dehazing (SID) algorithms have achieved better performances by creating a mapping function from haze to haze-free images. Usually, the images taken from the natural scenes ...
Comments