Publications | Mohab Kishawy

2026

Under Review

VeilGS: Solving Darkness as a Veil of 2D Basis Maps over Retinex 3DGS

Mohab Kishawy, Chengzhou Tang, Shahram Shirani, and Jun Chen

2026

Under review. Manuscript available on request
ICPR
RetinexDual: Retinex-Based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration

Mohab Kishawy, Ali Abdellatif Hussein, and Jun Chen

In Proceedings of the 28th International Conference on Pattern Recognition (ICPR), Aug 2026

Abs Paper Code Bib

Advancements in image sensing have elevated the importance of Ultra-High-Definition Image Restoration (UHD IR). Traditional methods, such as extreme downsampling or transformation from the spatial to the frequency domain, encounter significant drawbacks: downsampling induces irreversible information loss in UHD images, while our frequency analysis reveals that pure frequency-domain approaches are ineffective for spatially confined image artifacts, primarily due to the loss of degradation locality. To overcome these limitations, we present RetinexDual, a novel Retinex theory-based framework designed for generalized UHD IR tasks. RetinexDual leverages two complementary sub-networks: the Scale-Attentive maMBA (SAMBA) and the Frequency Illumination Adaptor (FIA). SAMBA, responsible for correcting the reflectance component, utilizes a coarse-to-fine mechanism to overcome the causal modeling of mamba, which effectively reduces artifacts and restores intricate details. On the other hand, FIA ensures precise correction of color and illumination distortions by operating in the frequency domain and leveraging the global context provided by it. Evaluating RetinexDual on four UHD IR tasks, namely deraining, deblurring, dehazing, and Low-Light Image Enhancement (LLIE), shows that it outperforms recent methods qualitatively and quantitatively. Ablation studies demonstrate the importance of employing distinct designs for each branch in RetinexDual, as well as the effectiveness of its various components.
@inproceedings{kishawy2026retinexdual, title = {{RetinexDual}: Retinex-Based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration}, author = {Kishawy, Mohab and Hussein, Ali Abdellatif and Chen, Jun}, booktitle = {Proceedings of the 28th International Conference on Pattern Recognition ({ICPR})}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, month = aug, year = {2026}, pages = {90--105}, doi = {10.1007/978-3-032-31335-5_7}, }
CVPRW
RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration

Mohab Kishawy and Jun Chen

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2026

NTIRE 2026: 4th and 5th Place Abs Paper Code Bib

RetinexDualV2 ranked 4th in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5th in the NTIRE 2026 Joint Denoising and Low-Light Image Enhancement (JDLLIE) track.

We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs a Task-Specific Physical Grounding Module (TS-PGM) to extract degradation-aware priors (e.g., rain masks and dark channels). These explicitly guide a Retinex decomposition network via a novel Physical-Conditioned Multi-head Self-Attention (PC-MSA) mechanism, enabling robust reflection and illumination correction. This physical conditioning allows a single architecture to handle various complex degradations seamlessly, without task-specific structural modifications. RetinexDualV2 demonstrates exceptional generalizability, securing 4th place in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5th place in the Joint Noise Low-light Enhancement (JNLLIE) Challenge. Extensive experiments confirm the state-of-the-art performance and efficiency of our physically motivated approach. Code is available at https://github.com/ErrorLogic1211/RetinexDual/tree/master/RetinexDualV2
@inproceedings{kishawy2026retinexdualv2, title = {{RetinexDualV2}: Physically-Grounded Dual Retinex for Generalized {UHD} Image Restoration}, author = {Kishawy, Mohab and Chen, Jun}, booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops}, month = jun, year = {2026}, pages = {1989--1998}, }

NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

Xin Li, Yeying Jin, Suhang Yao, Beibei Lin, Zhaoxin Fan, Wending Yan, 28 more authors, Mohab Kishawy, and 63 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2026

4th Place Abs Paper Bib

Our team (RetinexDualV2) ranked 4th in the challenge.

This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this challenge attracted a wide range of impressive solutions, all developed and evaluated on our real-world Raindrop Clarity dataset. For this edition, we adjust the dataset with 14,139 images for training, 407 images for validation, and 593 images for testing. The primary goal of this challenge is to establish a strong and practical benchmark for the removal of raindrops under various illumination and focus conditions. In total, 168 teams have registered for the competition, and 17 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating the growing progress in this challenging task. The project website is available at https://lixinustc.github.io/CVPR-NTIRE2026-RainDrop-Competition.github.io/.

@inproceedings{li2026ntire_raindrop,
  title = {{NTIRE} 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results},
  author = {Li, Xin and Jin, Yeying and Yao, Suhang and Lin, Beibei and Fan, Zhaoxin and Yan, Wending and Jin, Xin and Wu, Zongwei and Li, Bingchen and Shi, Peishu and Wang, Yufei and Li, Yu and Chen, Zhibo and Wen, Bihan and Tan, Robby T. and Timofte, Radu and Li, Runzhe and Jiang, Kui and Yu, Zhaocheng and Chen, Yiang and Jiang, Junjun and Liu, Xianming and Gu, Hongde and Li, Zeliang and You, Mache and Dong, Jiangxin and Pan, Jinshan and Rong, Qiyu and Shao, Bowen and Jing, Hongyuan and Zhang, Mengmeng and Ding, Bo and Zhang, Hui and Ren, Yi and Kishawy, Mohab and Chen, Jun and Duong, Anh-Kiet and Gomez-Kramer, Petra and Carozza, Jean-Michel and Xing, Wangzhi and Lu, Xin and Gu, Enxuan and Zhang, Jingxi and Chen, Diqi and Yi, Qiaosi and Wei, Bingcai and Li, Wenjie and Tie, Bowen and Guo, Heng and Ma, Zhanyu and Tu, Jiachen and Xu, Guoyi and Jiang, Yaoxin and Liu, Cici and Shi, Yaokun and Garrido Mellado, Paula and Feijoo, Daniel and Garcia Lara, Alvaro and Conde, Marcos V. and Zhu, Zhidong and Xiong, Bangshu and Ou, Qiaofeng and Rao, Zhibo and Li, Wei and Zhang, Zida and Geng, Hui and Xu, Qisheng and Deng, Xuyao and Wang, Changjian and Xu, Kele and Dong, Guanglu and Zhao, Qiyao and Zheng, Tianheng and Li, Chunlei and Mou, Lichao and Ren, Chao and Peng, Chang-De and Tsai, Chieh-Yu and Liu, Guan-Cheng and Kang, Li-Wei and Rajak, Abhishek and Singh, Milan Kumar and Kumar, Ankit and Sonone, Dimple and Upla, Kishor and Raja, Kiran and Zhao, Huilin and Xu, Xing and Chen, Chuan and Lao, Yeming and Xun, Wenjing and Yang, Li and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Yang, Hao and Zhang, Ruikun and Pan, Liyuan},
  booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},
  month = jun,
  year = {2026},
  pages = {2054--2070},
}

CVPRW

Low Light Image Enhancement Challenge at NTIRE 2026

George Ciubotariu, Sharif S M A, Abdur Rehman, Fayaz Ali Dharejo, Rizwan Ali Naqvi, Marcos V Conde, 79 more authors, Mohab Kishawy, and 5 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2026

5th Place (JDLLIE) Abs Paper Bib

Our team (RetinexDualV2) ranked 5th in Track 2: Joint Denoising and Low-Light Image Enhancement (JDLLIE).

This paper presents a comprehensive review of the NTIRE 2026 Low Light Image Enhancement Challenge, highlighting the proposed solutions and final results. The objective of this challenge is to identify effective networks capable of producing clearer and visually compelling images in diverse and challenging conditions, by learning representative visual cues with the purpose of restoring information loss due to low-contrast and noisy images. A total of 195 participants registered for the first track and 153 for the second track of the competition, and 22 teams ultimately submitted valid entries. This paper thoroughly evaluates the state-of-the-art advances in (joint denoising and) low-light image enhancement, showcasing the significant progress in the field, while leveraging samples of our novel dataset.

@inproceedings{ciubotariu2026ntire_lowlight,
  title = {Low Light Image Enhancement Challenge at {NTIRE} 2026},
  author = {Ciubotariu, George and A, Sharif S M and Rehman, Abdur and Dharejo, Fayaz Ali and Naqvi, Rizwan Ali and Conde, Marcos V and Timofte, Radu and Jin, Zhi and Wu, Hongjun and Zhang, Wenjian and Ye, Chang and Yi, Xunpeng and Yan, Qinglong and Zhang, Yibing and Akalwadi, Nikhil and I Pattanshetty, Varda and I Pattanshetty, Varsha and Desai, Padmashree and Mudenagudi, Uma and Tabib, Ramesh Ashok and Yang, Hao and Zhang, Ruikun and Pan, Liyuan and Kinli, Furkan and Ryou, Donghun and Ha, Inju and Kang, Junoh and Han, Bohyung and Zhou, Wei and Haitman, Yuval and Lapid, Ariel and Peretz, Reuven and Diamant, Idit and Cao, Leilei and Zhang, Shuo and Hambarde, Praful and Shaily, Prateek and Kumar, Jayant and Sharma, Hardik and Negi, Aashish and Chaudhary, Sachin and Dudhane, Akshay and Shukla, Amit and Wu, MoHao and Wang, Lin and Tu, Jiachen and Xu, Guoyi and Jiang, Yaoxin and Liu, Jiajia and Shi, Yaokun and Balmez, Raul and Brateanu, Alexandru and Orhei, Ciprian and Ancuti, Cosmin and Ancuti, Codruta O. and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Qiao, Kaifan and Chen, Bofei and Xu, Jingyi and Zhang, Duo and Deng, Xin and Xu, Mai and Li, Shengxi and Jiang, Lai and A, Harini and N, Ananya and K, Lakshanya and Xu, Ying and Zhu, Xinyi and Shi, Shijun and Zhang, Jiangning and Liu, Yong and Hu, Kai and Xu, Jing and Zeng, Xianfang and Song, Jinao and Tang, Guangsheng and Li, Cheng and Yang, Yuqiang and Wang, Ziyi and Chen, Yan and Bao, Long and Sun, Heng and Kishawy, Mohab and Chen, Jun and Siu, Wan-Chi and Cheng, Yihao and Lee, Man Hammond and Hui, Chun-Chuen},
  booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},
  month = jun,
  year = {2026},
  pages = {1741--1753},
}

CVPRW

NTIRE 2026 Nighttime Image Dehazing Challenge Report

Radu P Ancuti, Alexandru Brateanu, Raul Balmez, Ciprian Orhei, Florin Alexandru Vasluianu, Codruta O Ancuti, 59 more authors, Mohab Kishawy, and 23 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2026

Abs Paper Bib

This report presents an overview and analysis of the NTIRE 2026 Challenge on Nighttime Image Dehazing. The challenge introduced a new benchmark dataset, NT-HAZE, specifically designed to address the complexities of dehazing under nighttime conditions. The dataset consists of 40 pairs of real hazy and corresponding haze-free images captured in diverse indoor nighttime scenes. Haze was generated using a professional setup that accurately reproduces atmospheric scattering effects, enabling the acquisition of aligned image pairs under identical illumination conditions and supporting reliable quantitative evaluation. The competition attracted 21 participating teams, whose methods were evaluated in the final phase. The proposed approaches reflect the current state of the art in image dehazing, with many leveraging advanced deep learning techniques. NT-HAZE dataset is available at https://github.com/NTIRE-HAZE/Nighttime-Image-Dehazing-NTIRE-2026.

@inproceedings{ancuti2026ntire_dehazing,
  title = {{NTIRE} 2026 Nighttime Image Dehazing Challenge Report},
  author = {Ancuti, Radu P and Brateanu, Alexandru and Balmez, Raul and Orhei, Ciprian and Vasluianu, Florin Alexandru and O Ancuti, Codruta and Timofte, Radu and Ancuti, Cosmin and Dong, Wei and Heydari, Mohammad and Zhou, Han and Chen, Jun and Pang, Li and Bai, Weichen and Wang, Hongzhong and Meng, Deyu and Cao, Xiangyong and Kim, Guisik and Park, Jinhee and Cho, Choongsang and Crivoi, Carla and Radoi, Anamaria and Zhang, Lize and Yin, Weiling and Yin, Hao and Wang, Luyang and Shi, Gege and Lu, Xin and Fu, Xueyang and Zha, Zhengjun and Wang, Hao and Feng, Chaoyu and Zou, Dongqing and Lei, Lei and Li, Xiaotian and Jing, Hongyuan and Ren, Yi and Xu, Jiajun and Shao, Bowen and Rong, Qiyu and Yang, Wenlu and Hu, Jinjin and Zhang, Hui and Zhang, Mengmeng and Huang, Biao and Zhuang, Kailin and Fu, Zhiheng and Zheng, Shuling and Zhang, Feng and Chen, Zhanglu and Yao, Boyang and Li, Zhan and Duon, Anh-Kiet and Krame, Petra Gomez- and Carozza, Jean-Michel and Manu, Chippy M. and G, Sreeni K. and Yuan, Weijun and Liu, Shuhong and Chang, Gengjia and Li, Xuyang and Dong, Guanqun and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Kishawy, Mohab and Sai, Thota Venkata and Trivedi, Daksh and Bhatt, Jeny and Mandali, Urja and Rammohan, Keerthisri Radha and Upla, Kishor and Raja, Kiran and Zhang, Ruikun and Pan, Liyuan and Shet, Tejas R. R. and Akalwadi, Nikhil and Tabib, Ramesh Ashok and Mudenagudi, Uma and V, Ashwin and Shraya, Madhu and Kumar, Aditya and Tu, Jiachen and Xu, Guoyi and Jiang, Yaoxin and Liu, Jiajia and Shi, Yaokun and Wang, Haodian and Ge, Xining},
  booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},
  month = jun,
  year = {2026},
  pages = {1608--1625},
}

CVPRW

Advances in Single-Image Shadow Removal: Results from the NTIRE 2026 Challenge

Florin-Alexandru Vasluianu, Tim Seizinger, Zhuyun Zhou, Zongwei Wu, Radu Timofte, Lorenzo Beltrame, 57 more authors, Mohab Kishawy, and 26 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2026

Abs Paper Bib

This work provides an analysis of the results from the NTIRE 2026 Shadow Removal Challenge and provides details from the best solutions. A total of 223 participants registered for the competition, of which 22 teams successfully submitted solutions during the final evaluation phase. The 2026 edition placed particular emphasis on quantitative performance assessment, using a balanced mix of metrics sensitive to strong perceptual quality under robust restoration fidelity. All submissions were evaluated on benchmark data from the WSRD+ dataset, showing complex interactions between self-shadows and cast shadows in scenes with large variety of objects, textures, and materials. The proposed data refinement strategies, coupled to task-specific tailored designs tackle a challenging image restoration task, finally showcasing the quality of the proposed solutions.

@inproceedings{vasluianu2026ntire_shadow,
  title = {Advances in Single-Image Shadow Removal: Results from the {NTIRE} 2026 Challenge},
  author = {Vasluianu, Florin-Alexandru and Seizinger, Tim and Zhou, Zhuyun and Wu, Zongwei and Timofte, Radu and Beltrame, Lorenzo and Salzinger, Jules and Svoboda, Filip and Lampert, Jasmin and Fanta-Jende, Phillipp and Körner, Marco and Hong, Binkai and Liu, Dingrui and Cao, Yang and Kwon, Junhyeong and Oh, Youngjin and Cho, Nam Ik and Shi, Shijun and Zhang, Jiangning and Liu, Yong and Hu, Kai and Xu, Jing and Zeng, Xianfang and Wang, Pan and Yang, Jingchu and Hu, Yihao and Ha, Inju and Ryou, Donghun and Kang, Junoh and Han, Bohyung and Mishra, Ujjwal and Hambarde, Kailash A. and Proença, Hugo and Chaudhary, Sachin and Hambarde, Praful and Shukla, Amit and Trivedi, Daksh and Singh, Divyavardhan and Mohammad, Hammad and Mittal, Mrudul and Upla, Kishor and Raja, Kiran and Park, Junyoung and Fan, Zihao and Zhou, Ziang and Jiang, Ruixuan and Bao, Yuanfei and Li, Dong and Lu, Xin and Fu, Xueyang and Zha, Zheng-Jun and Duong, Anh-Kiet and Gomez-Krämer, Petra and Carozza, Jean-Michel and Joshi, Amogh and Meesiyawar, Saiprasad and Akalwadi, Nikhil and Tabib, Ramesh Ashok and Mudenagudi, Uma and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Kim, June and Kishawy, Mohab and Chen, Jun and Tu, Jiachen and Shi, Yaokun and Xu, Guoyi and Jiang, Yaoxin and Liu, Jiajia and Shin, Asuka and Shigematsu, Kosuke and Shirono, Hiroto and Moori, Ahmad and Akbarpour, Hadi Ali and Yang, Hao and Zhang, Ruikun and Pan, Liyuan and Cai, Huaming and Brateanu, Alexandru and Balmez, Raul and Orhei, Ciprian and Ancuti, Codruta Orniana and Ancuti, Cosmin and Zhao, Suiyi and Zhou, Jinxing and Zhou, Yanghao and Yang, Yufeng and Huang, Jiancheng and Zhou, Donghao},
  booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},
  month = jun,
  year = {2026},
  pages = {2582--2595},
}

2025

CVPRW

NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results

Xiaoning Liu, Zongwei Wu, Florin-Alexandru Vasluianu, Hailong Yan, Bin Ren, Yulun Zhang, 15 more authors, Mohab Kishawy, and 83 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2025

2nd Place Abs Paper Bib

Our team (Imagine) ranked 2nd overall and 1st in PSNR.

This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.

@inproceedings{liu2025ntire,
  title = {{NTIRE} 2025 Challenge on Low Light Image Enhancement: Methods and Results},
  author = {Liu, Xiaoning and Wu, Zongwei and Vasluianu, Florin-Alexandru and Yan, Hailong and Ren, Bin and Zhang, Yulun and Gu, Shuhang and Zhang, Le and Zhu, Ce and Timofte, Radu and Shi, Kangbiao and Feng, Yixu and Hu, Tao and Cao, Yu and Wu, Peng and Liang, Yijin and Zhang, Yanning and Yan, Qingsen and Zhou, Han and Dong, Wei and Min, Yan and Kishawy, Mohab and Chen, Jun and Yu, Pengpeng and Park, Anjin and Lee, Seung-Soo and Park, Young-Joon and Hu, Zixiao and Liu, Junyv and Zhang, Huilin and Zhang, Jun and Wan, Fei and Xu, Bingxin and Liu, Hongzhe and Xu, Cheng and Pan, Weiguo and Dai, Songyin and Yi, Xunpeng and Yan, Qinglong and Zhang, Yibing and Ma, Jiayi and Hu, Changhui and Hu, Kerui and Jing, Donghang and Chen, Tiesheng and Jin, Zhi and Wu, Hongjun and Huang, Biao and Ling, Haitao and Wu, Jiahao and Zhan, Dandan and Rao, G Gyaneshwar and Aralikatti, Vijayalaxmi Ashok and Akalwadi, Nikhil and Tabib, Ramesh Ashok and Mudenagudi, Uma and Lin, Ruirui and Huang, Guoxi and Anantrasirichai, Nantheera and Yang, Qirui and Brateanu, Alexandru and Orhei, Ciprian and Ancuti, Cosmin and Feijoo, Daniel and Benito, Juan C. and Garcia, Alvaro and Conde, Marcos V. and Qin, Yang and Balmez, Raul and Ali, Anas M. and Benjdira, Bilel and Boulila, Wadii and Mao, Tianyi and Zheng, Huan and Wei, Yanyan and Tang, Shengeng and Guo, Dan and Zhang, Zhao and Nathan, Sabari and Uma, K and Sasithradevi, A and Bama, B Sathya and Roomi, S. Mohamed Mansoor and Li, Ao and Zhang, Xiangtao and Liu, Zhe and Tang, Yijie and Tang, Jialong and Fu, Zhicheng and Chen, Gong and Nasti, Joe and Nicholson, John and Xiao, Zeyu and Li, Zhuoyuan and Kulkarni, Ashutosh and Patil, Prashant W. and Vipparthi, Santosh Kumar and Murala, Subrahmanyam and Liu, Duan and Li, Weile and Lu, Hangyuan and Liu, Rixian and Wang, Tengfeng and Liang, Jinxing and Yu, Chenxin},
  booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},
  month = jun,
  year = {2025},
  pages = {1196--1206},
  doi = {10.1109/CVPRW67362.2025.00114},
}

2024

Sci. Rep.
Federated Learning System on Autonomous Vehicles for Lane Segmentation

Mohab M. Eid Kishawy, Mohamed T. Abd El-Hafez, Retaj Yousri, and M. Saeed Darweesh

Scientific Reports, Oct 2024

Abs Paper Code Bib

Autonomous Vehicles (AV) is one of the most evolving industries in the last decade. However, one of the bottlenecks of this evolution is providing data that contains different scenarios and scenes to improve the models without exposing the privacy and security of the edge vehicles. The authors of this research propose a secure and efficient novel solution for lane segmentation in AVs through the use of Federated Learning (FL). FedLane involves initial training of U-Net, ResUNet, and ResUNet++ models, followed by real-time inference in edge devices and the application of FL to update the server model using clients’ data. The study found that FL has enhanced the performance of lane segmentation significantly over baseline, enabling decentralized privacy-preserving collaborative optimization with increased dice coef from 0.9429 to 0.9794 for U-Net, from 0.9291 to 0.9854 for ResUNet and from 0.9079 to 0.9675 for ResUNet++. Additionally, the models show increased stability over the training iterations, highlighting the potential of FL to play a significant role in the future of automation in the AV industry.
@article{eid2024federated, title = {Federated Learning System on Autonomous Vehicles for Lane Segmentation}, author = {Eid Kishawy, Mohab M. and Abd El-Hafez, Mohamed T. and Yousri, Retaj and Darweesh, M. Saeed}, journal = {Scientific Reports}, volume = {14}, number = {1}, pages = {25029}, month = oct, year = {2024}, publisher = {Nature Publishing Group}, doi = {10.1038/s41598-024-71187-8}, }

CVPRW

NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Report

Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu, Radu Timofte, Yidi Liu, Xingbo Wang, 17 more authors, Mohab Kishawy, and 44 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2024

4th Place Abs Paper Bib

Our team (ITB Dehaze) ranked 4th in the challenge.

This study examines the results of the NTIRE 2024 Challenge on Dense and Non-Homogeneous Dehazing. Innovative methods were introduced and tested using a new image dataset named DNH-HAZE. The DNH-HAZE dataset comprises 50 pairs of authentic outdoor images showcasing dense and non-homogeneous haze alongside corresponding haze-free images of identical scenes. The haze was simulated using a professional setup designed to mirror real-world hazy conditions. The competition attracted 374 participants with 16 teams presenting solutions for the final evaluation phase. The proposed solutions showed the leading edge of image dehazing technology.

@inproceedings{ancuti2024ntire,
  title = {{NTIRE} 2024 Dense and Non-Homogeneous Dehazing Challenge Report},
  author = {Ancuti, Codruta O. and Ancuti, Cosmin and Vasluianu, Florin-Alexandru and Timofte, Radu and Liu, Yidi and Wang, Xingbo and Zhu, Yurui and Shi, Gege and Lu, Xin and Fu, Xueyang and Zha, Zheng-Jun and Dong, Wei and Zhou, Han and Wang, Ruiyi and Liu, Xiaohong and Zhai, Guangtao and Chen, Jun and Song, Wei and Gao, Yichang and Xiong, Jiahao and Lin, Hualiang and Li, Xianger and Li, Dong and Kishawy, Mohab and Li, Ruibin and Mousavi, Seyed Amirreza and Rauf, Rana and Liu, Yangyi and Liu, Huan and Tu, Mingsheng and Xu, Kele and Chen, Jiawen and Xu, Qisheng and Sun, Tao and Guo, Jin and Shao, Ben and Liu, Tianli and Wu, Mohao and Yan, Xingzhuo and Fu, Minghan and Yang, Lehan and Lin, Xin and Qi, Lu and Song, Jincen and Hu, Xiaoqian and Tao, Linwai and Chen, Hongming and Chen, Xiang and Xie, Chuanlong and Zhang, Zhao and Wang, Junhu and Wei, Yanyan and Zhao, Suiyi and Tang, Shengeng and Malagi, Sampada and Joshi, Amogh and Akalwadi, Nikhil and Desai, Chaitra and Tabib, Ramesh Ashok and Mudenagudi, Uma and Jiang, Wenjing and Kalyanshetti, Jagadeesh and Aralikatti, Vijayalaxmi Ashok and P, Yashaswini and Upasi, Nitish and Hegde, Dikshit and Patil, Ujwala and C, Sujata},
  booktitle = {Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},
  month = jun,
  year = {2024},
  pages = {6453--6468},
  doi = {10.1109/CVPRW63382.2024.00646},
}

2022

IEEE Access

A Generic AI-Based Technique for Assessing Student Performance in Conducting Online Virtual and Remote Controlled Laboratories

Ahmed M. Abd El-Haleem, Mohab Mohammed Eid, Mahmoud M. Elmesalawy, and Hadeer A. Hassan Hosny

IEEE Access, 2022

Paper Code Bib

@article{abdelhaleem2022generic,
  title = {A Generic {AI}-Based Technique for Assessing Student Performance in Conducting Online Virtual and Remote Controlled Laboratories},
  author = {Abd El-Haleem, Ahmed M. and Eid, Mohab Mohammed and Elmesalawy, Mahmoud M. and Hosny, Hadeer A. Hassan},
  journal = {{IEEE} Access},
  volume = {10},
  pages = {128046--128065},
  year = {2022},
  doi = {10.1109/ACCESS.2022.3227505},
}

CICN

A New Intelligent System for Evaluating and Assisting Students in Laboratory Learning Management System

Hadeer A. Hassan, Mohab Mohamed Eid, Mahmoud M. Elmesalawy, and Ahmed M. Abd El-Haleem

In Proceedings of the 14th International Conference on Computational Intelligence and Communication Networks (CICN), Dec 2022

Paper Code Bib

@inproceedings{hassan2022new,
  title = {A New Intelligent System for Evaluating and Assisting Students in Laboratory Learning Management System},
  author = {Hassan, Hadeer A. and Eid, Mohab Mohamed and Elmesalawy, Mahmoud M. and Abd El-Haleem, Ahmed M.},
  booktitle = {Proceedings of the 14th International Conference on Computational Intelligence and Communication Networks ({CICN})},
  publisher = {IEEE},
  month = dec,
  year = {2022},
  pages = {566--571},
  doi = {10.1109/CICN56167.2022.10008322},
}

2021

IJAMC

Using Machine Learning Algorithms for Breast Cancer Diagnosis

Mazen Mobtasem El-Lamey, Mohab Mohammed Eid, Muhammad Gamal, Nour-Elhoda Mohamed Bishady, and Ali Wagdy Mohamed

International Journal of Applied Metaheuristic Computing, Oct 2021

Paper Bib

@article{ellamey2021using,
  title = {Using Machine Learning Algorithms for Breast Cancer Diagnosis},
  author = {El-Lamey, Mazen Mobtasem and Eid, Mohab Mohammed and Gamal, Muhammad and Bishady, Nour-Elhoda Mohamed and Mohamed, Ali Wagdy},
  journal = {International Journal of Applied Metaheuristic Computing},
  volume = {12},
  number = {4},
  pages = {117--137},
  month = oct,
  year = {2021},
  publisher = {IGI Global},
  doi = {10.4018/ijamc.2021100107},
}

Springer

Modelling and Analysis the Population Density Effect on the Infectiousness Rate of COVID-19 Novel Virus and the Mortality Rate Percentage Regarding Oxford’s Stringency Index Model of Governmental Response in MATLAB

Amira Mofreh Ibrahim, Nour El Hoda Mohamed Bishady, Samar Hassan Elghalban, Nagham Nessim Mostafa, Mohab Mohamed Eid, and Khaled Mohamed Abdelhamid

In Artificial Intelligence for COVID-19, 2021

Paper Bib

@incollection{ibrahim2021modelling,
  title = {Modelling and Analysis the Population Density Effect on the Infectiousness Rate of {COVID}-19 Novel Virus and the Mortality Rate Percentage Regarding {Oxford}'s Stringency Index Model of Governmental Response in {MATLAB}},
  author = {Ibrahim, Amira Mofreh and Bishady, Nour El Hoda Mohamed and Elghalban, Samar Hassan and Mostafa, Nagham Nessim and Eid, Mohab Mohamed and Abdelhamid, Khaled Mohamed},
  booktitle = {Artificial Intelligence for {COVID}-19},
  editor = {Oliva, Diego and Hassan, Said Ali and Mohamed, Ali},
  series = {Studies in Systems, Decision and Control},
  publisher = {Springer},
  year = {2021},
  pages = {437--462},
  doi = {10.1007/978-3-030-69744-0_25},
}

2020

NILES

Modeling the Effect of Population Density on Controlling COVID-19 Initial Spread with the Use of MATLAB Numerical Methods and Stringency Index Model

Amira Mofreh Ibrahim, Mohab Mohammed Eid, Nagham Nessim Mostafa, Nour El-Hoda Mohamed Bishady, and Samar Hassan Elghalban

In Proceedings of the 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES), Oct 2020

Paper Bib

@inproceedings{ibrahim2020modeling,
  title = {Modeling the Effect of Population Density on Controlling {COVID}-19 Initial Spread with the Use of {MATLAB} Numerical Methods and Stringency Index Model},
  author = {Ibrahim, Amira Mofreh and Mohammed Eid, Mohab and Mostafa, Nagham Nessim and Mohamed Bishady, Nour El-Hoda and Elghalban, Samar Hassan},
  booktitle = {Proceedings of the 2nd Novel Intelligent and Leading Emerging Sciences Conference ({NILES})},
  publisher = {IEEE},
  month = oct,
  year = {2020},
  pages = {612--617},
  doi = {10.1109/NILES50944.2020.9257960},
}