HarmoDehazeDiffusion: Multi-Scale Spatial Fusion Network for Dense Haze Removal
Source abstract
Abstract
Image dehazing remains a critical yet challenging task in computer vision. While the existing dehazing methods have achieved notable progress, they still struggle to effectively eliminate dense haze in scenes while maintaining consistent illumination between dehazed regions and their surroundings. To address these challenges, we propose a novel image dehazing framework named HarmoDehazeDiffusion. Our model first acquires a depth map of an input image and then integrates these depth cues with hazy images to guide the diffusion denoising process. To simultaneously tackle dense haze removal and illumination consistency, we innovatively incorporate a multi-scale feature extraction strategy, coupled with an adaptive spatial fusion mechanism. Extensive experiments conducted on multiple public benchmarks demonstrate that HarmoDehazeDiffusion achieves a state-of-the-art performance. Quantitative and qualitative evaluations reveal our method’s superior capability to remove haze while preserving natural consistency in the illumination compared to that of the existing approaches, particularly in challenging dense haze scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fire Detection and Safety Systems · Video Surveillance and Tracking Methods · Image Enhancement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China
School of Electrical Engineering, Guangxi University, Nanning 530004, China
References (47)
Show source-provided references
1. McCartney, E.J. (1976). Optics of the Atmosphere: Scattering by Molecules and Particles, Wiley.
2. Single image haze removal using dark channel prior
3. Dehazing using color-lines10.1145/2651362 ↗
4. Zhu, Q., Mai, J., and Shao, L. (2014, January 1–5). Single image dehazing using color attenuation prior. Proceedings of the BMVC, Nottingham, UK.10.5244/C.28.114 ↗
5. Chen, C., Do, M.N., and Wang, J. (2016, January 11–14). Robust image and video dehazing with visual artifact suppression via gradient residual minimization. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part II 14.10.1007/978-3-319-46475-6_36 ↗
6. Zhang, J., Cao, Y., Fang, S., Kang, Y., and Wen Chen, C. (2017, January 21–26). Fast haze removal for nighttime image using maximum reflectance prior. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.742 ↗
7. Berman, D., and Avidan, S. (July, January 26). Non-local image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
8. Li, B., Peng, X., Wang, Z., Xu, J., and Feng, D. (2017, January 22–29). Aod-net: All-in-one dehazing network. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.511 ↗
9. Dehazenet: An end-to-end system for single image haze removal10.1109/TIP.2016.2598681 ↗
10. Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., and Yang, M.H. (2016, January 11–14). Single image dehazing via multi-scale convolutional neural networks. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part II 14.
11. Zhang, H., and Patel, V.M. (2018, January 18–23). Densely connected pyramid dehazing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00337 ↗
12. Learning aggregated transmission propagation networks for haze removal and beyond10.1109/TNNLS.2018.2862631 ↗
13. Liu, Y., Pan, J., Ren, J., and Su, Z. (November, January 27). Learning deep priors for image dehazing. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
14. Guo, C.L., Yan, Q., Anwar, S., Cong, R., Ren, W., and Li, C. (2022, January 18–24). Image dehazing transformer with transmission-aware 3D position embedding. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00572 ↗
15. Liu, X., Ma, Y., Shi, Z., and Chen, J. (November, January 27). Griddehazenet: Attention-based multi-scale network for image dehazing. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
16. Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X., Wang, F., and Yang, M.H. (2020, January 13–19). Multi-scale boosted dehazing network with dense feature fusion. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00223 ↗
17. Wu, H., Qu, Y., Lin, S., Zhou, J., Qiao, R., Zhang, Z., Xie, Y., and Ma, L. (2021, January 20–25). Contrastive learning for compact single image dehazing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01041 ↗
18. Yu, H., Zheng, N., Zhou, M., Huang, J., Xiao, Z., and Zhao, F. (2022, January 23–27). Frequency and spatial dual guidance for image dehazing. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-19800-7_11 ↗
19. Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior10.1109/TIP.2016.2612882 ↗
20. Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., and Yang, M.H. (2018, January 18–23). Gated fusion network for single image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00343 ↗
21. Deng, Q., Huang, Z., Tsai, C.C., and Lin, C.W. (2020, January 23–28). Hardgan: A haze-aware representation distillation gan for single image dehazing. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58539-6_43 ↗
22. Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2020, January 7–12). FFA-Net: Feature fusion attention network for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.6865 ↗
23. Yu, H., Huang, J., Liu, Y., Zhu, Q., Zhou, M., and Zhao, F. (2022, January 10–14). Source-free domain adaptation for real-world image dehazing. Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal.10.1145/3503161.3548410 ↗
24. Liu, H., Wu, Z., Li, L., Salehkalaibar, S., Chen, J., and Wang, K. (2022, January 18–24). Towards multi-domain single image dehazing via test-time training. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00574 ↗
25. FSAD-Net: Feedback spatial attention dehazing network10.1109/TNNLS.2022.3146004 ↗
26. Multiscale cross-connected dehazing network with scene depth fusion10.1109/TNNLS.2022.3184164 ↗
27. Zheng, Y., Zhan, J., He, S., Dong, J., and Du, Y. (2023, January 17–24). Curricular contrastive regularization for physics-aware single image dehazing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00560 ↗
28. Wu, R.Q., Duan, Z.P., Guo, C.L., Chai, Z., and Li, C. (2023, January 17–24). Ridcp: Revitalizing real image dehazing via high-quality codebook priors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.02134 ↗
29. Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S. (2015, January 7–9). Deep unsupervised learning using nonequilibrium thermodynamics. Proceedings of the International Conference on Machine Learning, PMLR, Lille, France.
30. Generative modeling by estimating gradients of the data distribution
31. Denoising diffusion probabilistic models
32. Nichol, A.Q., and Dhariwal, P. (2021, January 18–24). Improved denoising diffusion probabilistic models. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.
33. Diffusion models beat gans on image synthesis
34. Image super-resolution via iterative refinement
35. Whang, J., Delbracio, M., Talebi, H., Saharia, C., Dimakis, A.G., and Milanfar, P. (2022, January 18–24). Deblurring via stochastic refinement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01581 ↗
36. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18–24). High-resolution image synthesis with latent diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01042 ↗
37. Piccinelli, L., Yang, Y.H., Sakaridis, C., Segu, M., Li, S., Van Gool, L., and Yu, F. (2024, January 16–22). UniDepth: Universal monocular metric depth estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.00963 ↗
38. Yang, Y., Wang, C., Liu, R., Zhang, L., Guo, X., and Tao, D. (2022, January 18–24). Self-augmented unpaired image dehazing via density and depth decomposition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00208 ↗
39. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
40. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 13–16). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.123 ↗
41. Benchmarking single-image dehazing and beyond10.1109/TIP.2018.2867951 ↗
42. Liu, Y., Zhu, L., Pei, S., Fu, H., Qin, J., Zhang, Q., Wan, L., and Feng, W. (2021, January 20–24). From synthetic to real: Image dehazing collaborating with unlabeled real data. Proceedings of the 29th ACM International Conference on Multimedia, Chengdu, China.10.1145/3474085.3475331 ↗
43. Ancuti, C.O., Ancuti, C., Sbert, M., and Timofte, R. (2019, January 22–25). Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.10.1109/ICIP.2019.8803046 ↗
44. DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention10.1109/TIP.2024.3354108 ↗
45. Hong, M., Liu, J., Li, C., and Qu, Y. (March, January 22). Uncertainty-driven dehazing network. Proceedings of the AAAI Conference on Artificial Intelligence, Online.
46. Vision transformers for single image dehazing10.1109/TIP.2023.3256763 ↗
47. Frequency compensated diffusion model for real-scene dehazing10.1016/j.neunet.2024.106281 ↗