Task-Aligned Haze Removal With Semantic-Aware Fusion and Contrast Self-Correction

Jinbin Wang , Aiping Yang , Guosong Jiang , Wenlong Yu , Dongwei Ren , Qinghua Hu

CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (4) : 978 -993.

PDF (5464KB)
CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (4) :978 -993. DOI: 10.1049/cit2.70162
ORIGINAL RESEARCH
research-article
Task-Aligned Haze Removal With Semantic-Aware Fusion and Contrast Self-Correction
Author information +
History +
PDF (5464KB)

Abstract

Adverse haze conditions introduce complex degradations that obscure scene details and distort structural cues critical for object detection, posing persistent challenges for vision-based sensing systems. Although existing haze removal methods have achieved notable improvements in visual clarity, their optimisation objectives are often misaligned with downstream detection requirements, leading to limited detection performance in real-world scenarios. To address this issue, this work proposes a task-aligned weakly supervised haze removal framework, termed Dehaze4Detection, which explicitly aligns low-level restoration with high-level detection objectives. The framework incorporates a Semantic-Aware Multi-Scale Fusion Module (SMFM) that embeds pixel-level semantic knowledge into the dehazing process, enabling selective enhancement of object regions while suppressing background over-enhancement to achieve detection-friendly restoration. To further improve feature quality, a Contrast Self-Correction Attention Module (CSAM) is introduced, which exploits contrast maps derived from pseudo-dehazed images to guide attention towards object contours and salient structures. The proposed SMFM and CSAM are integrated into a unified pipeline and jointly optimised using detection and dehazing losses. Extensive experiments on both synthetic and real-world benchmarks demonstrate that Dehaze4Detection achieves competitive perceptual quality while significantly improving detection accuracy.

Keywords

contrast self-correction / haze removal / low-level vision / semantic fusion / task-aligned

Cite this article

Download citation ▾
Jinbin Wang, Aiping Yang, Guosong Jiang, Wenlong Yu, Dongwei Ren, Qinghua Hu. Task-Aligned Haze Removal With Semantic-Aware Fusion and Contrast Self-Correction. CAAI Transactions on Intelligence Technology, 2026, 11 (4) : 978-993 DOI:10.1049/cit2.70162

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Q. Zhang, J. Xiao, C. Tian, J. C.-W. Lin, and S. Zhang, “ A Robust Deformed Convolutional Neural Network (CNN) for Image Denoising,” CAAI Transactions on Intelligence Technology 8, no. 2 (2023): 331-342, https://doi.org/10.1049/cit2.12110.

[2]

C. Tian, X. Zhang, Qi Zhang, M. Yang, and Z. Ju, “ Image Super-Resolution via Dynamic Network,” CAAI transactions on intelligence technology 9, no. 4 (2024): 837-849, https://doi.org/10.1049/cit2.12297.

[3]

B. Goyal, A. Dogra, D. C. Lepcha, et al., “ Recent Advances in Image Dehazing: Formal Analysis to Automated Approaches,” Information Fusion 104 (2024): 102151, https://doi.org/10.1016/j.inffus.2023.102151.

[4]

A. Murtaza, U. Khairuddin, A.’A. Mohd Faudzi, K. Hamamoto, Y. Fang, and Z. Omar, “ WaveLiteDehaze-Network: A Low-Parameter Wavelet-Based Method for Real-Time Dehazing,” CAAI Transactions on Intelligence Technology 10, no. 4 (2025): 1033-1048, https://doi.org/10.1049/cit2.70011.

[5]

Z. He, P. Wang, Y. Zou, et al., “ Dadigan: Aa Dual Attention Blocks-Based Disentangled Iterative Generative Adversarial Network for Cloud and Shadow Removal on SAR and Optical Images,” Information Fusion 125 (2026): 103487, https://doi.org/10.1016/j.inffus.2025.103487.

[6]

T. Jia, J. Li, Li Zhuo, and T. Yu, “ Semi-Supervised Single-Image Dehazing Network via Disentangled Meta-Knowledge,” IEEE Transactions on Multimedia 26 (2023): 2634-2647, https://doi.org/10.1109/tmm.2023.3301273.

[7]

Yu Dong, Y. Li, Q. Dong, He Zhang, and S. Chen, “ Semi-Supervised Domain Alignment Learning for Single Image Dehazing,” IEEE Transactions on Cybernetics 53, no. 11 (2022): 7238-7250, https://doi.org/10.1109/tcyb.2022.3221544.

[8]

K. He, J. Sun, and X. Tang, “ Single Image Haze Removal Using Dark Channel Prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence 33, no. 12 (2010): 2341-2353, https://doi.org/10.1109/TPAMI.2010.168.

[9]

Q. Zhu, J. Mai, and L. Shao, “ A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior,” IEEE Transactions on Image Processing 24, no. 11 (2015): 3522-3533, https://doi.org/10.1109/tip.2015.2446191.

[10]

D. Berman and S. Avidan, “ Non-Local Image Dehazing,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 1674-1682.

[11]

B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, “ Dehazenet: An End-to-End System for Single Image Haze Removal,” IEEE Transactions on Image Processing 25, no. 11 (2016): 5187-5198, https://doi.org/10.1109/tip.2016.2598681.

[12]

B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng, “ Aod-Net: All-In-One Dehazing Network,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017), 4770-4778.

[13]

X. Yin, G. Tu, and Q. Chen, “ Multiscale Depth Fusion With Contextual Hybrid Enhancement Network for Image Dehazing,” IEEE Transactions on Instrumentation and Measurement 72 (2023): 1-12, https://doi.org/10.1109/tim.2023.3318748.

[14]

Z. Lihe, J. He, Q. Yuan, X. Jin, Y. Xiao, and L. Zhang, “ Phdnet: A Novel Physic-Aware Dehazing Network for Remote Sensing Images,” Information Fusion 106 (2024): 102277, https://doi.org/10.1016/j.inffus.2024.102277.

[15]

Y. Song, Z. He, H. Qian, and X. Du, “ Vision Transformers for Single Image Dehazing,” IEEE Transactions on Image Processing 32 (2023): 1927-1941, https://doi.org/10.1109/tip.2023.3256763.

[16]

Z. Wang, X. Cun, J. Bao, W. Zhou, J. Liu, and H. L. Uformer, “ A General u-Shaped Transformer for Image Restoration,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), 17683-17693.

[17]

Y. Wang, J. Xiong, X. Yan, and M. Wei, “ Uscformer: Unified Transformer With Semantically Contrastive Learning for Image Dehazing,” IEEE Transactions on Intelligent Transportation Systems 24, no. 10 (2023): 11321-11333, https://doi.org/10.1109/tits.2023.3277709.

[18]

W. Yu, Q. Wang, C. Liu, L. Dong, and Q. Hu, “ Coe: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification,” in Proceedings of the Computer Vision and Pattern Recognition Conference (2025), 4364-4374.

[19]

C. Tian, T. Cheng, Y. Ma, Z. Qi, B. Zhang, and D. Zhang, “ A Heterogeneous CNN With Transformers for Image Denoising,” IEEE Transactions on Consumer Electronics 72, no. 2 (2026): 2658-2667, https://doi.org/10.1109/tce.2026.3665312.

[20]

Y. Fan, Y. Wang, M. Wei, F. L. Wang, and H. Xie, “ Friendnet: Detection-Friendly Dehazing Network,” preprint, arXiv:2403.04443 (2024), https://arxiv.org/html/2403.04443v1.

[21]

Y. Wan, J. Li, L. Lin, Q. Yuan, and H. Shen, “ Collaboration of Dehazing and Object Detection Tasks: A Multi-Task Learning Framework for Foggy Image,” IEEE Transactions on Geoscience and Remote Sensing (2025), https://doi.org/10.1109/TGRS.2025.3548283.

[22]

B. Li, W. Ren, D. Fu, et al., “ Benchmarking Single-Image Dehazing and Beyond,” IEEE Transactions on Image Processing 28, no. 1 (2018): 492-505, https://doi.org/10.1109/tip.2018.2867951.

[23]

C. Sakaridis, D. Dai, and L. Van Gool, “ Semantic Foggy Scene Understanding With Synthetic Data,” International Journal of Computer Vision 126, no. 9 (2018): 973-992, https://doi.org/10.1007/s11263-018-1072-8.

[24]

W. Ren, Si Liu, H. Zhang, J. Pan, X. Cao, and M.-H. Yang, “ Single Image Dehazing via Multi-Scale Convolutional Neural Networks,” in European Conference on Computer Vision (ECCV) (Springer, 2016), 154-169.

[25]

Y. Qu, Y. Chen, J. Huang, and Y. Xie, “ Enhanced pix2pix Dehazing Network,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 8160-8168.

[26]

D. Chen, M. He, Q. Fan, et al., “ Gated Context Aggregation Network for Image Dehazing and Deraining,” in 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) (IEEE, 2019), 1375-1383.

[27]

X. Liu, Y. Ma, Z. Shi, and J. Chen, “ Griddehazenet: Attention-Based Multi-Scale Network for Image Dehazing,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019), 7314-7323.

[28]

H. Dong, J. Pan, L. Xiang, et al., “ Multi-Scale Boosted Dehazing Network With Dense Feature Fusion,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 2157-2167.

[29]

Xu Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, “ Ffa-Net: Feature Fusion Attention Network for Single Image Dehazing,” Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 7 (2020): 11908-11915, https://doi.org/10.1609/aaai.v34i07.6865.

[30]

H. Wu, Y. Qu, S. Lin, et al., “ Contrastive Learning for Compact Single Image Dehazing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 10551-10560.

[31]

C.-Le Guo, Q. Yan, S. Anwar, R. Cong, W. Ren, and C. Li, “ Image Dehazing Transformer With Transmission-Aware 3d Position Embedding,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), 5812-5820.

[32]

S. Zhao, L. Zhang, Y. Shen, and Y. Zhou, “ Refinednet: A Weakly Supervised Refinement Framework for Single Image Dehazing,” IEEE Transactions on Image Processing 30 (2021): 3391-3404, https://doi.org/10.1109/tip.2021.3060873.

[33]

Ye Liu, L. Zhu, S. Pei, et al., “ From Synthetic to Real: Image Dehazing Collaborating With Unlabeled Real Data,” in Proceedings of the ACM International Conference on Multimedia (MM) (2021), 50-58.

[34]

A. Golts, D. Freedman, and M. Elad, “ Unsupervised Single Image Dehazing Using Dark Channel Prior Loss,” IEEE Transactions on Image Processing 29 (2019): 2692-2701, https://doi.org/10.1109/tip.2019.2952032.

[35]

B. Li, Y. Gou, J. Z. Liu, H. Zhu, J. T. Zhou, and Xi Peng, “ Zero-Shot Image Dehazing,” IEEE Transactions on Image Processing 29 (2020): 8457-8466, https://doi.org/10.1109/tip.2020.3016134.

[36]

D. Engin, A. Genç, and H. K. Ekenel, “ Cycle-Dehaze: Enhanced Cyclegan for Single Image Dehazing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2018).

[37]

B. Li, Y. Gou, S. Gu, J. Z. Liu, J. T. Zhou, and X. Peng, “ You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network,” International Journal of Computer Vision 129, no. 5 (2021): 1754-1767, https://doi.org/10.1007/s11263-021-01431-5.

[38]

Y. Shao, L. Li, W. Ren, C. Gao, and N. Sang, “ Domain Adaptation for Image Dehazing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 2808-2817.

[39]

H. Yu, J. Huang, Y. Liu, Q. Zhu, M. Zhou, and F. Zhao, “ Source-Free Domain Adaptation for Real-World Image Dehazing,” in Proceedings of the ACM International Conference on Multimedia (MM) (2022), 6645-6654.

[40]

Y. Wang, X. Yan, K. Zhang, et al., “ Togethernet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning,” Computer Graphics Forum 41, no. 7 (2022): 465-476, https://doi.org/10.1111/cgf.14692.

[41]

C. Li, H. Zhou, Y. Liu, et al., “ Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes,” IEEE Transactions on Pattern Analysis and Machine Intelligence 45, no. 7 (2023): 8284-8295, https://doi.org/10.1109/TPAMI.2023.3234976.

[42]

Y. Zhu, T. Wang, X. Fu, et al., “ Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), 21747-21758.

[43]

Z. Zhang, L. Zhao, Y. Liu, S. Zhang, and J. Yang, “ Unified Density-Aware Image Dehazing and Object Detection in Real-World Hazy Scenes,” in Proceedings of the Asian Conference on Computer Vision (ACCV) (2020), 119-135.

[44]

W. Liu, G. Ren, R. Yu, S. Guo, J. Zhu, and L. Zhang, “ Image-Adaptive Yolo for Object Detection in Adverse Weather Conditions,” Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (2022): 1792-1800, https://doi.org/10.1609/aaai.v36i2.20072.

[45]

S. Kalwar, D. Patel, A. Aanegola, K. Reddy Konda, S. Garg, and K. M. Krishna, “ Gdip: Gated Differentiable Image Processing for Object Detection in Adverse Conditions,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2023), 7083-7089.

[46]

H. Zhang, L. Xiao, X. Cao, and H. Foroosh, “ Multiple Adverse Weather Conditions Adaptation for Object Detection via Causal Intervention,” IEEE Transactions on Pattern Analysis and Machine Intelligence 46, no. 3 (2022): 1742-1756, https://doi.org/10.1109/tpami.2022.3166765.

[47]

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “ Pyramid Scene Parsing Network,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017), 2881-2890.

[48]

Y. Zhang, Y. Tian, Y. Kong, B. Zhong, and Y. Fu, “ Residual Dense Network for Image Super-Resolution,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018), 2472-2481.

[49]

G. Jocher, A. Stoken, J. Borovec, et al., “ ultralytics/yolov5: v3.0,” Zenodo [Online] (2020), https://doi.org/10.5281/zenodo.3983579.

[50]

A. Yang, Y. Liu, J. Wang, et al., “ Visual-Quality-Driven Unsupervised Image Dehazing,” Neural Networks 167 (2023): 1-9, https://doi.org/10.1016/j.neunet.2023.08.010.

[51]

J.-P. Tarel and N. Hautiere, “ Fast Visibility Restoration From a Single Color or Gray Level Image,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (IEEE, 2009), 2201-2208.

[52]

Y. Su, N. Wang, Z. Cui, Y. Cai, C. He, and A. Li, “ Real Scene Single Image Dehazing Network With Multi-Prior Guidance and Domain Transfer,” IEEE Transactions on Multimedia (2025).

[53]

H. Wang, Y. Xu, Y. He, et al., “ Yolov5-fog: A Multiobjective Visual Detection Algorithm for Fog Driving Scenes Based on Improved yolov5,” IEEE Transactions on Instrumentation and Measurement 71 (2022): 1-12, https://doi.org/10.1109/tim.2022.3196954.

[54]

Z.-D. Zhang, B. Zhang, Z.-C. Lan, et al., “ Finet: An Insulator Dataset and Detection Benchmark Based on Synthetic Fog and Improved yolov5,” IEEE Transactions on Instrumentation and Measurement 71 (2022): 1-8, https://doi.org/10.1109/tim.2022.3194909.

PDF (5464KB)

0

Accesses

0

Citation

Detail

Sections
Recommended

/

〈 〉