Aditya Arora

I am an ELLIS PhD student co-supervised by Prof. Marcus Rohrbach and Dr. Pau Rodriguez at TU Darmstadt, Germany. My research interests include making Efficient Video Generation models.

I completed my Masters at York University, co-supervised by Prof. Konstantinos G Derpanis and Prof. Michael S Brown. I was a Research Engineer at Inception Institute of Artificial Intelligence working with Dr. Fahad Shahbaz Khan and Dr. Syed Waqas Zamir, where I worked on various low-level vision taks such as Image Denoising, Image Enhancement and Image Super-Resolution.

I interned at Snap Inc. New York City with Dr. Sizhuo Ma and Dr. Jian Wang where I worked on Efficient Diffusion Models for Image Super-Resolution. I have also been a Research Intern at Indian Institute of Technology, Roorkee where I worked with Dr. Balasubramanian Raman on Acoustic Scene Classification.

adityadvlp at gmail dot com
CV / Scholar / Github / Linkedin

News

[Jul’24]Our paper GuideSR is accepted at ICCVW 2025.
[Jun’24]Our paper Image Fusion White Balance is accepted at ICCV 2025.
[Mar’25]Started my ELLIS PhD at MAI Lab, TU Darmstadt under Prof. Marcus Rohrbach and Dr. Pau Rodriguez.
[Sep’24]Successfully defender my Masters Thesis Image White Balance for Multi-Illuminant Scenes at York University.
[Jul’24]Doing an internship at Snap Inc. New York City, under Dr. Sizhuo Ma and Dr. Jian Wang.
[Jun’24]Our paper OVTAL is accepted at BMVC 2024.
[Apr’24]We achieved 3rd position in CVPR-NTIRE 2024 Blind Enhancement of Compressed Image Challenge.
[Sep'22]Started my Masters at CVIL Lab, York University under Prof. Konstantinos G Derpanis and Prof. Michael S Brown.
[Apr’22]Our paper MIRNetV2 is accepted at TPAMI.
[Mar’22]Our paper Restormer is accepted at CVPR’22 as an oral presentation.
[Apr’21]MPRNet inspired winning solutions in CVPR-NTIRE 2021 for Dual-pixel Defocus Deblurring and Image Deblurring Challenges.
[Apr’21]We achieved 2nd position in CVPR-NTIRE 2021 Dual-Pixel Defocus Deblurring Challenge.
[Mar’21]Our paper MPRNet is accepted at CVPR’21.
[Jul’20]Our paper MIRNet is accepted at ECCV’20.
[Mar’20]Our papers CycleISP (Oral) and AnimalWeb are accepted at CVPR’20.
[Aug’19]A Large-scale Instance Segmentation Dataset for Aerial Images (iSAID) is available for download.
[Apr’19]We achieved 2nd position in CVPR-NTIRE 2019 Image Enhancement Challenge.
Publications

2025
GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution
Aditya Arora, Zhengzhong Tu, Yufei Wang, Ruizheng Bai, Jian Wang, Sizhuo Ma
arXiv preprint, 2025
arxiv / bibtex 
@article{arora2025guidesr,
    title={GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution},
    author={Arora, Aditya and Tu, Zhengzhong and Wang, Yufei and Bai, Ruizheng and Wang, Jian and Ma, Sizhuo},
    journal={arXiv preprint arXiv:2505.00687},
    year={2025}
    }
Revisiting Image Fusion for Multi-Illuminant White-Balance Correction
David Serrano-Lozano, Aditya Arora, Luis Herranz, Konstantinos G. Derpanis,
Michael S. Brown, Javier Vazquez-Corral
International Conference on Computer Vision (ICCV), 2025
arxiv / bibtex 
@article{serrano2025revisiting,
    title={Revisiting Image Fusion for Multi-Illuminant White-Balance Correction},
    author={Serrano-Lozano, David and Arora, Aditya and Herranz, Luis and Derpanis, Konstantinos G and Brown, Michael S and Vazquez-Corral, Javier},
    journal={arXiv preprint arXiv:2503.14774},
    year={2025}
    }

2024
Open-Vocabulary Temporal Action Localization using Multimodal Guidance
Akshita Gupta, Aditya Arora, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Graham W. Taylor
British Machine Vision Conference (BMVC), 2024
arxiv / bibtex 
@article{gupta2024open,
    title={Open-vocabulary temporal action localization using multimodal guidance},
    author={Gupta, Akshita and Arora, Aditya and Narayan, Sanath and Khan, Salman and Khan, Fahad Shahbaz and Taylor, Graham W},
    journal={arXiv preprint arXiv:2406.15556},
    year={2024}
    }

2022
Learning Enriched Features for Fast Image Restoration and Enhancement
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
arxiv / bibtex / code 
@article{zamir2022mirnetv2,
    title={Learning Enriched Features for Fast Image Restoration and Enhancement},
    author={Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat
            and Fahad Shahbaz Khan and Ming-Hsuan Yang},
    journal={TPAMI},
    year={2022}
    }
Restormer: Efficient Transformer for High-Resolution Image Restoration
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang
Computer Vision and Pattern Recognition (CVPR), 2022
arxiv / bibtex / code 
@inproceedings{Zamir2021Restormer,
    title={Restormer: Efficient Transformer for High-Resolution Image Restoration},
    author={Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat
            and Fahad Shahbaz Khan and Ming-Hsuan Yang},
    booktitle={CVPR},
    year={2022}
    }

2021
Multi-Stage Progressive Image Restoration
Syed Waqas Zamir*, Aditya Arora*, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan,
Ming-Hsuan Yang, Ling Shao
Computer Vision and Pattern Recognition (CVPR), 2021
arxiv / bibtex / code 
@inproceedings{Zamir2021MPRNet,
    title={Multi-Stage Progressive Image Restoration},
    author={Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat
            and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
    booktitle={CVPR},
    year={2021}
    }

2020
Learning Enriched Features for Real Image Restoration and Enhancement
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan,
Ming-Hsuan Yang, Ling Shao
European Conference on Computer Vision (ECCV), 2020
arxiv / bibtex / code 
@inproceedings{Zamir2020MIRNet,
    title={Learning Enriched Features for Real Image Restoration and Enhancement},
    author={Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat
            and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
    booktitle={ECCV},
    year={2020}
    }
CycleISP: Real Image Restoration via Improved Data Synthesis
Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan,
Ming-Hsuan Yang, Ling Shao
Computer Vision and Pattern Recognition (CVPR), 2020
arxiv / bibtex / code 
@inproceedings{Zamir2020CycleISP,
    title={CycleISP: Real Image Restoration via Improved Data Synthesis},
    author={Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat
            and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
    booktitle={CVPR},
    year={2020}
    }
AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces
Muhammad Haris Khan, John McDonagh, Salman Khan, Muhammad Shahabuddin,
Aditya Arora, Fahad Shahbaz Khan, Ling Shao, Georgios Tzimiropoulos
Computer Vision and Pattern Recognition (CVPR), 2020
arxiv / bibtex / project 
@inproceedings{khan2020animalweb,
    title={Animalweb: A large-scale hierarchical dataset of annotated animal faces},
    author={Muhammad Haris Khan and John McDonagh and Salman Khan
            and Muhammad Shahabuddin and Aditya Arora and Fahad Shahbaz Khan
            and Ling Shao and Georgios Tzimiropoulos},
    booktitle={CVPR},
    year={2020}
    }

2019
iSAID: A large-scale dataset for instance segmentation in aerial images
Syed Waqas Zamir*, Aditya Arora*, Akshita Gupta, Salman Khan, Guolei Sun,
Fahad Shahbaz Khan, Fan Zhu, Ling Shao, Gui-Song Xia, Xiang Bai
Computer Vision and Pattern Recognition Workshops (CVPRW), 2019
arxiv / bibtex / code / project 
@inproceedings{waqas2019isaid,
    title={isaid: A large-scale dataset for instance segmentation in aerial images},
    author={Syed Waqas Zamir and Aditya Arora and Akshita Gupta and Salman Khan
            and Guolei Sun and Fahad Shahbaz Khan and Fan Zhu and Ling Shao
            and Gui-Song Xia and Xiang Bai},
    booktitle={CVPR Workshops},
    year={2019}
    }
Learning digital camera pipeline for extreme low-light imaging
Syed Waqas Zamir, Aditya Arora, Salman Khan, Fahad Shahbaz Khan, Ling Shao
Neurocomputing, 2021
arxiv / bibtex 
@article{zamir2019learning,
    title={Learning digital camera pipeline for extreme low-light imaging},
    author={Syed Waqas Zamir and Aditya Arora and Salman Kha
            and Fahad Shahbaz Khan and Ling Shao},
    journal={arXiv preprint arXiv:1904.05939},
    year={2019}
    }

2018
Acoustic features fusion using attentive multi-channel deep architecture
Gaurav Bhatt, Akshita Gupta, Aditya Arora, Balasubramanian Raman
Interspeech Workshops, 2018
arxiv / bibtex / code 
@article{bhatt2018acoustic,
    title={Acoustic features fusion using attentive multi-channel deep architecture},
    author={Gaurav Bhatt and Akshita Gupta and Aditya Arora and Balasubramanian Raman},
    journal={arXiv preprint arXiv:1811.00936},
    year={2018}
    }

Built on GitHub pages