IRO Journals
Journal of Innovative Image Processing

Contrast and Visibility Enhancement of Weather-Degraded Images Using Dual-Branch CNN and Transformer with Perceptual Loss for ADAS

Open Access
Published: 29 June, 2026
Pages: 786-809
  • Anmol Jain , Anmol Jain
    Department of Computer Science and Engineering, Noida International University, Gautam Budh Nagar, Uttar Pradesh, India
    Department of Computer Science and Engineering, Noida International University, Gautam Budh Nagar, Uttar Pradesh, India
  • Veerendra Yadav , Veerendra Yadav
    Department of Computer Science and Engineering, Noida International University, Gautam Budh Nagar, Uttar Pradesh, India
    Department of Computer Science and Engineering, Noida International University, Gautam Budh Nagar, Uttar Pradesh, India
  • Harsh Khatter Harsh Khatter
    Department of Computer Science and Information Technology, Krishna Institute of Engineering & Technology (KIET), Ghaziabad, Delhi-NCR, Uttar Pradesh, India
    Department of Computer Science and Information Technology, Krishna Institute of Engineering & Technology (KIET), Ghaziabad, Delhi-NCR, Uttar Pradesh, India
view PDF
view PDF

How to Cite

Jain, Anmol, Veerendra Yadav, and Harsh Khatter. 2026. “Contrast and Visibility Enhancement of Weather-Degraded Images Using Dual-Branch CNN and Transformer With Perceptual Loss for ADAS”. Journal of Innovative Image Processing 8 (3): 786-809. https://doi.org/10.36548/jiip.2026.3.003.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Dual-Branch CNN
Transformer
Perceptual Loss
Visibility Enhancement
Adverse Weather
ADAS

Abstract

Weather can be either poor or good. Poor weather, includING fog, hazE, rain, or low light, can cause dramatic degradation of image perception in road-level situations, leading to with significant performance loss in camera-based Advanced Driver-Assistance Systems (ADAS), Although traditional improvement techniques relying on Convolutional Networks (CNNs) cannot effectively preserve global context in image appearance improvement, techniques using transformers show high computational costs. This restricts their application as real-time system efficiency becomes critically important. In this paper, we propose a solution using the Dual-Branch CNN Transformer, which uniformly utilizes localized spatial features extraction together with global semantic modeling using parallel experience sharing of Convolutional Networks and Self Attention Mechanisms. An adaptive gated fusion module integrates these complementary local and global representations through learnable spatial weighting, while perceptual-loss-guided optimization emphasizes texture fidelity, structural consistency, and visual realism. The model was tested on real-world driving image datasets such as BDD100K and KITTI Foggy Datasets and compared with state-of-the-art dehaze networks and general weather condition restoration networks. The proposed model achieved a PSNR of 36.5 dB, an SSIM of 0.962, and an LPIPS of 0.081 while recording an inference latency of 42 ms/frame, corresponding to 23.8 FPS (~24 FPS) on an NVIDIA RTX 4090 GPU. Qualitative evaluation further demonstrated improved restoration of lane boundaries, vehicle contours, and overall scene coherence under adverse weather conditions. These findings indicate that the proposed framework provides an efficient and perceptually robust solution for visibility enhancement in autonomous driving scenarios.

References

  1. Shit, Sahadeb, and Dip Narayan Ray. "Review and Evaluation of Recent Advancements in Image Dehazing Techniques for Vision Improvement and Visualization." Journal of Electronic Imaging 32, no. 5 (2023): 050901-050901.
  2. Brophy, Tim, Darragh Mullins, Ashkan Parsi, Jonathan Horgan, Enda Ward, Patrick Denny, Ciarán Eising, Brian Deegan, Martin Glavin, and Edward Jones. "A Review of the Impact of Rain on Camera-Based Perception in Automated Driving Systems." IEEE Access 11 (2023): 67040-67057.
  3. An, Shunmin, Xixia Huang, Lujia Cao, and Linling Wang. "A Comprehensive Survey on Image Dehazing for Different Atmospheric Scattering Models." Multimedia Tools and Applications 83, no. 14 (2024): 40963-40993.
  4. Yang, Jiangang, Jianfei Yang, Luqing Luo, Yun Wang, Shizheng Wang, and Jian Liu. "Robust Visual Recognition in Poor Visibility Conditions: A Prior Knowledge-Guided Adversarial Learning Approach." Electronics 12, no. 17 (2023): 3711.
  5. Shree, AM Deepthi, and M. Brindha. "Image Restoration and Object Detection in Unfavourable Weather Conditions for Autonomous Vehicles Using Deep Learning Approaches: A Review." In 8th International Conference on Computing in Engineering and Technology (ICCET 2023), vol. 2023, pp. 73-83. IET, 2023.
  6. Tahir, Noor Ul Ain, Zuping Zhang, Muhammad Asim, Junhong Chen, and Mohammed ELAffendi. "Object Detection in Autonomous Vehicles Under Adverse Weather: A Review of Traditional and Deep Learning Approaches." Algorithms 17, no. 3 (2024): 103.
  7. Shi, Yining, Kun Jiang, Jiusi Li, Zelin Qian, Junze Wen, Mengmeng Yang, Ke Wang, and Diange Yang. "Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review." IEEE Transactions on Neural Networks and Learning Systems 36, no. 7 (2024): 11814-11834.
  8. Hao, Fangwei, Ji Du, Weiyun Liang, Jing Xu, and Xiaoxuan Xu. "Towards Context-Aware Convolutional Network for Image Restoration." Knowledge-Based Systems 321 (2025): 113579.
  9. Ali, Anas M., Bilel Benjdira, Anis Koubaa, Walid El-Shafai, Zahid Khan, and Wadii Boulila. "Vision Transformers in Image Restoration: A Survey." Sensors 23, no. 5 (2023): 2385.
  10. Yang, Mengmeng, Lay Sheng Ewe, Weng Kean Yew, Sanxing Deng, and Sieh Kiong Tiong. "A Survey of Data Augmentation Techniques for Traffic Visual Elements." Sensors 25, no. 21 (2025): 6672.
  11. Zhu, John. Enabling Simulation-Driven Development of Control Policies for Lower-Limb Robotic Prosthesis. North Carolina State University, 2025.
  12. Chen, Li, Penghao Wu, Kashyap Chitta, Bernhard Jaeger, Andreas Geiger, and Hongyang Li. "End-To-End Autonomous Driving: Challenges and Frontiers." IEEE Transactions on Pattern Analysis and Machine Intelligence 46, no. 12 (2024): 10164-10183.
  13. Jha, Ankit, Shirsha Bose, and Biplab Banerjee. "GAF-Net: Improving the Performance of Remote Sensing Image Fusion Using Novel Global Self and Cross Attention Learning." In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp. 6354-6363. 2023.
  14. Dai, Chenggang, Mingxing Lin, Xiaojian Wu, and Dong Zhang. "Single Hazy Image Restoration Using Robust Atmospheric Scattering Model." Signal Processing 166 (2020): 107257.
  15. Khan, Hira, Bin Xiao, Weisheng Li, and Nazeer Muhammad. "Recent Advancement in Haze Removal Approaches." Multimedia Systems 28, no. 3 (2022): 687-710.
  16. Luo, Xiyuan, Sen Wang, Jinpeng Liu, Xue Dong, Piao He, Qingyu Yang, Xi Chen et al. "Revolutionizing Optical Imaging: Computational Imaging via Deep Learning." Photonics Insights 4, no. 2 (2025): R03-R03.
  17. Patil, Kundan, Shrushti Kale, Jaivanti Dhokey, and Abhishek Gulhane. "Deepfake Detection Using Biological Features: A Survey." arXiv preprint arXiv:2301.05819 (2023).
  18. Muhammad, Khan, Tanveer Hussain, Hayat Ullah, Javier Del Ser, Mahdi Rezaei, Neeraj Kumar, Mohammad Hijji, Paolo Bellavista, and Victor Hugo C. De Albuquerque. "Vision-Based Semantic Segmentation in Scene Understanding for Autonomous Driving: Recent Achievements, Challenges, and Outlooks." IEEE Transactions on Intelligent Transportation Systems 23, no. 12 (2022): 22694-22715.
  19. Zhu, Ruoxi, Zhengzhong Tu, Jiaming Liu, Alan C. Bovik, and Yibo Fan. "Mwformer: Multi-Weather Image Restoration Using Degradation-Aware Transformers." IEEE Transactions on Image Processing 33 (2024): 6790-6805.
  20. Hao, Fangwei, Ji Du, Weiyun Liang, Jing Xu, and Xiaoxuan Xu. "Towards Context-Aware Convolutional Network for Image Restoration." Knowledge-Based Systems 321 (2025): 113579.
  21. Abdulmaksoud, Ahmed, and Ryan Ahmed. "Transformer-Based Sensor Fusion for Autonomous Vehicles: A Comprehensive Review." IEEE Access (2025).
  22. Prodan, Marcel, Giorgiana Violeta Vlăsceanu, and Costin-Anton Boiangiu. "Comprehensive Evaluation of Metrics for Image Resemblance." Journal of Information Systems & Operations Management 17, no. 1 (2023): 161-185.
  23. Bruno, Diego Renan, Rafael A. Berri, Felipe M. Barbosa, and Fernando S. Osório. "CARINA Project: Visual Perception Systems Applied for Autonomous Vehicles and Advanced Driver Assistance Systems (ADAS)." IEEE Access 11 (2023): 69720-69749.
  24. Fan, Liming, Anis Salwa Mohd Khairuddin, HaiChuan Liu, and Khairunnisa Binti Hasikin. "Perceptual Carlini-Wagner Attack: A Robust and Imperceptible Adversarial Attack Using LPIPS." IEEE Access (2025).
  25. Cancedda, Christian. "DA-Panopticfpn: A Panoptic Segmentation Model to Bridge the Gap Between Simulated and Real Autonomous Driving Perception Data." PhD diss., Politecnico di Torino, 2022.
  26. Ahmed, Hafiz M. Mubeen, Sohail Masood Bhatti, and Fawad Nasim. "Object Identification for Autonomous Vehicles Using Machine Learning." Journal of Computing & Biomedical Informatics 7, no. 01 (2024): 364-376.
  27. Tang, Minan, Zixin Zhao, and Jiandong Qiu. "A Foggy Weather Simulation Algorithm for Traffic Image Synthesis Based on Monocular Depth Estimation." Sensors 24, no. 6 (2024): 1966.
  28. Baldeva, Vaibhav, Vishakha Sharma, Satakshi Verma, Priya Kansal, Sachin Kansal, and Jyotindra Narayan. "Pixel-Dehaze: Deciphering Dehazing Through Regression-Based Depth and Scattering Estimation." Big Data and Cognitive Computing 9, no. 11 (2025): 282.
  29. Zhou, Shihao, Duosheng Chen, Jinshan Pan, Jinglei Shi, and Jufeng Yang. "Adapt or Perish: Adaptive Sparse Transformer With Attentive Feature Refinement for Image Restoration." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, 2952-2963.
  30. Chen, Yanfei, Tong Yue, Pei An, Hanyu Hong, Tao Liu, Yangkai Liu, and Yihui Zhou. "ICAFormer: An Image Dehazing Transformer Based on Interactive Channel Attention." Sensors 25, no. 12 (2025): 3750.
  31. Zhang, Lei, Xiang Du, Renran Zhang, and Jian Zhang. "A Lightweight Detection Algorithm for Unmanned Surface Vehicles Based on Multi-Scale Feature Fusion." Journal of Marine Science and Engineering 11, no. 7 (2023): 1392.
  32. Zamir, Syed Waqas, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. "Restormer: Efficient Transformer for High-Resolution Image Restoration." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, 5728-5739.
  33. An, Tao, Hongbo Gao, Ruqi Liu, Kun Dai, Tao Xie, Ruifeng Li, Ke Wang, and Lijun Zhao. "An Moe-Driven Unified Image Restoration Framework for Adverse Weather Conditions." IEEE Transactions on Circuits and Systems for Video Technology (2025).
  34. Zhao, Wenwen, Yikun Yang, Hao Hu, Yanzhan Chen, and Fan Yu. "A Lightweight Intrusion Detection Approach for CAN Bus Using Depthwise Separable Convolutional Kolmogorov Arnold Network." Scientific Reports 15, no. 1 (2025): 17550.
  35. Xie, Dirui, He Xiao, Xiaofang Hu, Yue Zhou, Guangdong Zhou, and Shukai Duan. "Neuromorphic Vision Restoration Network for Advanced Driver Assistance System." IEEE Transactions on Consumer Electronics 70, no. 1 (2024): 3658-3668.
  36. Hamed, Suhaib Kh, Mohd Juzaiddin Ab Aziz, and Mohd Ridzwan Yaakub. "A Review of Fake News Detection Approaches: A Critical Analysis of Relevant Studies and Highlighting Key Challenges Associated With The Dataset, Feature Representation, and Data Fusion." Heliyon 9, no. 10 (2023).
  37. Li, Haifeng, Wang Guo, Haiyang Wu, Mengwei Wu, Jipeng Zhang, Qing Zhu, Yu Liu, Xin Huang, and Chao Tao. "Remote Sensing Image Intelligent Interpretation from A Language-Centered Perspective: Principles, Methods, and Challenges." IEEE Geoscience and Remote Sensing Magazine (2026).
  38. Qian, Chenghao, Mahdi Rezaei, Saeed Anwar, Wenjing Li, Tanveer Hussain, Mohsen Azarmi, and Wei Wang. "Allweather-Net: Unified Image Enhancement for Autonomous Driving Under Adverse Weather and Low-Light Conditions." In International Conference on Pattern Recognition. Cham: Springer Nature Switzerland, 2024, 151-166.
  39. Wang, Wei, Pei Zhao, Weimin Lei, and Yingjie Ju. "Acmamba: A State Space Model-Based Approach for Multi-Weather Degraded Image Restoration." Electronics 13, no. 21 (2024): 4294.
  40. Zhang, Richard, Phillip Isola, Alexei A. Efros, Eli Shechtman, and Oliver Wang. "The Unreasonable Effectiveness of Deep Features as A Perceptual Metric." In Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, 586-595.
  41. Liu, Lu, Huiyu Duan, Qiang Hu, Liu Yang, Chunlei Cai, Tianxiao Ye, Huayu Liu, Xiaoyun Zhang, and Guangtao Zhai. "F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration." In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2025, 10982-10994.
  42. Bar Hillel, Aharon, Ronen Lerner, Dan Levi, and Guy Raz. "Recent progress in road and lane detection: a survey." Machine Vision and Applications 25, no. 3 (2014): 727-745.
  43. Yenikaya, Sibel, Gökhan Yenikaya, and Ekrem Düven. "Keeping The Vehicle on the Road: A Survey On On-Road Lane Detection Systems." ACM Computing Surveys (Csur) 46, no. 1 (2013): 1-43.
  44. Yu, Fisher, Haofeng Chen, Xin Wang, Wenqi Xian, Yingying Chen, Fangchen Liu, Vashisht Madhavan, and Trevor Darrell. "Bdd100k: A Diverse Driving Dataset for Heterogeneous Multitask Learning." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020, 2636-2645.
  45. Zhang, Bingli, Yixin Wang, Chengbiao Zhang, Junzhao Jiang, Xiang Luo, Xinyu Wang, Yangyang Zhang et al. "Fogfusion: Robust 3D Object Detection Based on Camera-Lidar Fusion for Autonomous Driving in Foggy Weather Conditions." Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 240, no. 4 (2026): 2312-2322.
  46. Li, Boyi, Xiulian Peng, Zhangyang Wang, Jizheng Xu, and Dan Feng. "Aod-Net: All-In-One Dehazing Network." In Proceedings of the IEEE international conference on computer vision. 2017, 4770-4778.
  47. Liu, Xiaohong, Yongrui Ma, Zhihao Shi, and Jun Chen. "Griddehazenet: Attention-Based Multi-Scale Network for Image Dehazing." In Proceedings of the IEEE/CVF international conference on computer vision. 2019, 7314-7323
  48. Valanarasu, Jeya Maria Jose, Rajeev Yasarla, and Vishal M. Patel. "Transweather: Transformer-Based Restoration of Images Degraded by Adverse Weather Conditions." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, 2353-2363.
  49. Zamir, Syed Waqas, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. "Restormer: Efficient Transformer for High-Resolution Image Restoration." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, 5728-5739.