I received my Ph.D. degrees in Computer Science from Wuhan University in 2024 under supervision of Prof. Lefei Zhang and currently a Postdoctoral Researcher at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) mentored by Prof. Salman Khan. I was a research intern at Horizon Robotics worked with Dr. Qian Zhang and Dr. Guoli Wang. I was also a visiting student in LV-Lab at NUS under supervision of Prof. Xinchao Wang.

My research interests include Vision for Natural Images (All-in-one Restoration), Raw Images (Neural ISP), Autonomous Driving Scene, and Remote Sensing Images (Hyperspectral).

📧 I am open to collaboration and welcome inquiries from anyone interested in my research topics. Feel free to reach out via jiaqi.ma AT mbzuai.ac.ae.

🔥 News

• 2026.03:  ✨ We win the 4th place in the first challenge on real-world all-in-one image restoration by LOVIF @CVPR 2026.
• 2026.02:  🎉 RainDiff is accepted by CVPR 2026. Congrats to all collaborators!
• 2026.01:  🎉 Simtoken is accepted by ICASSP 2026. Congrats to all collaborators!
• 2025.12:  ✨ Token Expand-Merge is on ArXiv now (Vision-Language-Action Models).
• 2025.12:  ✨ ClusIR is on ArXiv now (All-in-one Image Restoration).
• 2025.12:  ✨ EvoIR is on ArXiv now (All-in-one Image Restoration).
• 2025.05:  🎉 Perceive-IR is accepted by TIP.
• 2025.04:  🎉 HyperSIGMA is accepted by TPAMI.
• 2024.12:  🥂 Starting from 2025, I will join MBZUAI as a postdoc associate working with Assoc. Prof. Salman Khan!
• 2024.09:  🥂 We release a project regarding with All-in-one Image Restoration. We are awlays updating those recent awesome methods on this arising task. The comprehensive survey on All-in-one Image Restoration is on the way, stay tune with us~
• 2024.08:  ✨ Perceive-IR is on ArXiv now (All-in-one Image Restoration).
• 2024.06:  ✨ HyperSIGMA is on ArXiv now (The First One Billion Params Remote Sensing Foundation Model!).
• 2023.06:  ✨ ProRes is on ArXiv now (All-in-one Image Restoration).
• 2023.04:  🎉 One paper is accepted by Neural Networks.
• 2022.06:  🎉 One paper is accepted by ACM MM 2022.
• 2021.03:  🎉 One paper is accepted by CVPR 2021.
• 2020.10:  🎉 One paper is accepted by Pattern Recognition.
• 2019.05:  🎉 One paper is accepted by IJCAI 2019.

📝 Publications

Note: * Equal contribution, ^ Corresponding authors.

TIP

• Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration

Xu Zhang*, Jiaqi Ma*, Guoli Wang, Qian Zhang, Huan Zhang, Lefei Zhang^.

Code, Project

we propose Perceive-IR, an all-in-one image restorer designed to achieve fine-grained quality control that enables restored images to more closely resemble their undistorted counterparts, regardless of the type or severity of degradation.

TPAMI

• HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model

Di Wang*, Meiqi Hu*, Yao Jin*, Yuchun Miao*, Jiaqi Yang*, Yichu Xu*, Xiaolei Qin*, Jiaqi Ma*, Lingyu Sun*, Chenxing Li*, Chuan Fu, Hongruixuan Chen, Chengxi Han^, Naoto Yokoya, Jing Zhang^, Minqiang Xu, Lin Liu, Lefei Zhang, Chen Wu^, Bo Du^, Dacheng Tao, Liangpei Zhang^.

Code

we introduce HyperSIGMA, a vision transformer-based foundation model for HSI interpretation, scalable to over a billion parameters.

Under review (TIP)

• ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration

Jiaqi Ma*, Tianheng Cheng*, Guoli Wang, Qian Zhang, Xinggang Wang, Lefei Zhang^.

Code, Project

We perform the first attempt to involve visual prompt into image restoration tasks and explore some new findings.

Neural Networks

• Restoration and Enhancement on Low Exposure Raw Images by Joint Demosaicing and Denoising

Jiaqi Ma, Guoli Wang, Lefei Zhang^, Qian Zhang.

We propose a joint demosaicing and denoising framework for restoring and enhancing low exposure raw images.

ACM MM 2022

• ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer

Jiaqi Ma, Shengyuan Yan, Lefei Zhang^, Guoli Wang, Qian Zhang.

Code

We propose an efficient transformer framework for raw image restoration.

CVPR 2021

• Pseudo Facial Generation with Extreme Poses for Face Recognition

Guoli Wang, Jiaqi Ma, Qian Zhang, Jiwen Lu^, Jie Zhou.

Code

We discover the residual in extreme poses and propose a light-weight plug-in for face recognition.

Pattern Recognition

• Discriminative subspace matrix factorization for multiview data clustering

Jiaqi Ma, Yipeng Zhang, Lefei Zhang^.

We extend PSMF to multi-view scenero and discuss the combination of supervised and unsupervised framework.

IJCAI 2019

• Pseudo Supervised Matrix Factorization in Discriminative Subspace

Jiaqi Ma, Yipeng Zhang, Lefei Zhang^, Bo Du, Dapeng Tao.

We discover the relationship between NMF and LDA and propose a pseudo supervised matrix factorization method (PSMF).

🏆 Honors and Awards

• 2023.10,   China National Scholarship   Ministry of Education of the People’s Republic of China.
• 2022.06,   CSC(China Scholarship Council) Scholarship   Ministry of Education of the People’s Republic of China.
• 2021.11,   Yisheng Scholarship   Wuhan University.
• 2021.06,   Outstanding Postgraduate   Wuhan University.
• 2019.11,   China National Scholarship   Ministry of Education of the People’s Republic of China.
• 2019.11,   First-Class Outstanding Scholarship for Postgraduate   Wuhan University.

📖 Educations

• 2021.09 - 2024.12, Ph.D. in Computer Science.   School of Computer Science, Wuhan University.

• 2018.09 - 2021.06, Master in Computer Science.   School of Computer Science, Wuhan University.

• 2014.09 - 2018.06, Bachelor in Computer Science.   School of Information Engineering, Zhengzhou University.

🔬 Internships

• 2020.10 - 2023.06,   Horizon Robotics   Research Intern.

🧾 Statistic