📚 Biography
Jinfan Hu is pursuing his Ph.D. degree in XPixel Group, Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS). He is now supervised by Prof. Chao Dong. He obtained his Bachelor and Master degrees in Mathematics (supervised by Prof. Ting-Zhu Huang and Prof. Liang-Jian Deng) from the University of Electronic Science and Technology of China (UESTC), Chengdu, China in 2019 and 2022. His research interests include low-level vision (LV) and AI interpretability.
🔥 Headlines
[08/2025] 🎉🎉🎉 We propose HYPIR: A Step Toward the Next Generation of Image Restoration
HYPIR introduces a simple yet powerful paradigm: fine-tuning a pre-trained diffusion model with adversarial (GAN) loss — no diffusion sampling, no extra adapters. This achieves an unprecedented balance of speed, fidelity, and quality. Initializing GAN training from a pre-trained diffusion model anchors the model near the natural image manifold, ensuring stable training, faster convergence, and superior results — all in a single forward pass.
Official Webpage: The high-speed, high-performance image restoration model is now available on 明犀AI and SupPixel AI.
[03/2025] 🎉🎉🎉 One paper is accepted by TPAMI
We propose a model/task-agnostic interpreting method (CEM) for low-level vision models, bringing causality analysis into the field. We hope this work contributes to a deeper understanding and enhancement of low-level vision models!
Key Insight: Correlation does not imply causation — only causal analysis reveals why.
[02/2025] 🎉🎉🎉 We revisit the generalization problem of low-level vision models
This paper demonstrates that the common strategy of blindly expanding the training set is ineffective. Instead, the key to better generalization lies in guiding the network to learn the image content rather than the degradation!
Takeaway: Teach networks to see the content, not just remove degradation.
[02/2025] 🎉🎉🎉 The book 《底层视觉之美》 has been published
Co-authored with my supervisor Prof. Chao Dong. We hope this book provides valuable insights for researchers and enthusiasts in the Low-level Vision field!
Available on: JD.com
[01/2024] 🎉🎉🎉 We release a groundbreaking image restoration method (SUPIR)
That harnesses the generative prior and the power of model scaling up. Our method demonstrates unprecedented performance in real-world image restoration tasks!
Experience it now: 明犀AI and SupPixel AI.
📝 Publications
Book
董超, 胡锦帆, 《底层视觉之美》，电子工业出版社，2025.
Selected Paper
X. Lin, F. Yu, J. Hu, Z. You, W. Shi, Jimmy S. Ren, J. Gu, C. Dong. Harnessing Diffusion-Yielded Score Priors for Image Restoration. ACM SIGGRAPH Asia, 2025. [Code][PDF]
J. Hu, J. Gu, S. Yao, F. Yu, Z. Li, Z. You, C. Lu, C. Dong. Interpreting Low-level Vision Models with Causal Effect Maps. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. [Code][PDF]
J. Hu*, Z. You*, J. Gu, K. Zhu, T. Xue, C. Dong. Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining. arXiv, 2025. [PDF]
F. Yu, J. Gu, J. Hu, Z. Li, and C. Dong. UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models. International Conference on Learning Representations (ICLR), 2025. [PDF]
F. Yu, J. Gu, Z. Li, J. Hu, X. Kong, X. Wang, J. He, Y. Qiao, and C. Dong. Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [Project Page][PDF]
Y. Liu, J. He, Y. Liu, X. Lin, F. Yu, J. Hu, Y. Qiao, and C. Dong. AdaptBIR: Adaptive Blind Image Restoration with Latent Diffusion Prior for Higher Fidelity. Pattern Recognition, 2024. [DOI]
R. Ran, L.-J. Deng, T.-X. Jiang, J.-F. Hu, J. Chanussot, and G. Vivone. GuidedNet: A General CNN Fusion Framework via High-resolution Guidance for Hyperspectral Image Super-resolution. IEEE Transactions on Cybernetics (TCYB), 2023. ESI Highly Cited [Code][PDF]
X. Liu*, J. Hu*, X. Chen, and C. Dong. UDC-UNet: Under-Display Camera Image Restoration via U-shape Dynamic Network. European Conference on Computer Vision Workshop (ECCVW), 2022. [Code][PDF]
J.-F. Hu, T.-Z. Huang, L.-J. Deng, H.-X. Dou, D. Hong, and G. Vivone. Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution. IEEE Geoscience and Remote Sensing Letters, 2022. ESI Highly Cited [Code][PDF]
S. Peng, L.-J. Deng, J.-F. Hu, and Y.-W. Zhuo. Source-Adaptive Discriminative Kernels based Network for Remote Sensing Pansharpening. International Joint Conferences on Artificial Intelligence (IJCAI), 2022. [Code][PDF]
J.-F. Hu, T.-Z. Huang, L.-J. Deng, T.-X. Jiang, G. Vivone, and J. Chanussot. Hyperspectral Image Super-Resolution via Deep Spatiospectral Attention Convolutional Neural Networks. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. ESI Highly Cited [Project Page][PDF]
Z.-C. Wu, T.-Z. Huang, L.-J. Deng, J.-F. Hu, and G. Vivone. VO+ Net: An Adaptive Approach Using Variational Optimization and Deep Learning for Panchromatic Sharpening. IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2021. [Project page][PDF]
(* Equal contributions)
📸 Products
For a comprehensive exploration of our technologies, visit our official websites: 明犀AI and SupPixel AI.
📖 Experiences
- 09/2022-present: Ph.D. student in computer science. (Supervisor: Prof. Chao Dong); Shenzhen Institute of Advanced Technology (SIAT), University of Chinese Academy of Sciences (UCAS)
- 09/2019-06/2022: Master student in mathematics. (Supervisor: Prof. Ting-Zhu Huang and Prof. Liang-Jian Deng); University of Electronic Science and Technology of China (UESTC)
- 09/2015-06/2019: Bachelor student in information and computing science; University of Electronic Science and Technology of China (UESTC)
🏆 Honors and Awards
- 2nd Place in ECCV MIPI 2022 Challenge on UDC image restoration, 2022
- National Scholarship, 2021
- National First Prize of CUMCM, 2017
💬 Academic Activities
Peer-Reviewer: CVPR, TPAMI, TIP, TCYB, TMM, TIFS, TGRS, GRSL, TCI...
