Xijun Wang

I'm a postdoctoral researcher at Purdue University, advised by Prof. Stanley H. Chan. My primary research interests are image/video enhancement and generation with generative AI. I received my M.S. and Ph.D. in Computer Science from Northwestern University in 2019 and 2024, advised by Prof. Aggelos K. Katsaggelos. I received my bachelor's degree in Communication Engineering from Yingcai Honors College, University of Electronic Science and Technology of China (UESTC) in 2017. I was a visiting student in the Department of Computer Science at the Univeristy of California, Santa Barbara in 2016.

I am currently focusing on generative AI for image and video enhancement and generation. I believe the intersection of generative AI and real-world applications holds tremendous potential and excitement. I am open to diverse forms of research collaboration, and please feel free to reach out to me if we share the same research interest.

Email / Scholar / LinkedIn

Research

Generative Image & Video

Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
Yu Yuan, Xijun Wang, Prateek Chennuri, Xingguang Zhang, Stanley H. Chan
CVPR (Highlight), 2025
project page / PDF

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics
Yu Yuan, Xijun Wang, Tharindu Wickremasinghe, Zeeshan Nadir, Bole Ma, Stanley H. Chan
Under Review
project page / PDF

Generative Restoration & Enhancement

Low-Light Enhancement and Denoising

Personalized Generative Low-light Image Denoising and Enhancement
Xijun Wang, Prateek Chennuri, Yu Yuan, Bole Ma, Xingguang Zhang, Dilshan Godaliyadda,
Hamid R. Sheikh, Stanley H. Chan
Under Review
project page / PDF

Blind Restoration

Generative Personalized Blind Face Restoration Enhanced by Physical Identity
Xijun Wang, Xingguang Zhang, Yu Yuan, Bole Ma, Prateek Chennuri, Stanley H. Chan
IEEE ICIP, 2025
PDF

Atmospheric Turbulence Removal

	Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation Xingguang Zhang, Nicholas Chimitt, Xijun Wang, Yu Yuan, Stanley H. Chan CVPR (Highlight), 2025 project page / PDF
	Astrophotography Turbulence Mitigation via Generative Models Joonyeoup Kim, Yu Yuan, Xingguang Zhang, Xijun Wang, Stanley H. Chan IEEE ICIP, 2025 PDF
	Real-World Atmospheric Turbulence Correction Via Domain Adaptation Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos IEEE ICIP (Oral), 2024 PDF
	Video Variational Deep Atmospheric Turbulence Correction Santiago López-Tapia, Xijun Wang, Aggelos K. Katsaggelos IEEE Access, 2024 PDF
	Atmospheric Turbulence Correction via Variational Deep Diffusion Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos IEEE MIPR (Oral), 2024 PDF
	Variational Deep Atmospheric Turbulence Correction for Video Santiago López-Tapia, Xijun Wang, Aggelos K. Katsaggelos IEEE ICIP, 2023 PDF

Super-Resolution

	Spatially-Aware Loss Functions for GAN-Driven Super-Resolution Xijun Wang, Santiago López-Tapia, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos IEEE Access, 2025 PDF
	Real-Time Lightweight Video Super-Resolution With RRED-Based Perceptual Constraint Xinyi Wu, Santiago López-Tapia, Xijun Wang, Aggelos K. Katsaggelos IEEE TCSVT, 2024 PDF
	Semantic Prior Based Generative Adversarial Network for Video Super-Resolution Xinyi Wu, Alice Lucas, Santiago Lopez-Tapia, Xijun Wang, Yul Hee Kim, Rafael Molina, Aggelos K. Katsaggelos EUSIPCO, 2019 PDF
	A Composite Discriminator for Generative Adversarial Network based Video Super-Resolution Xijun Wang, Alice Lucas, Santiago Lopez-Tapia, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos EUSIPCO, 2019 PDF
	Spatially Adaptive Losses for Video Super-resolution with GANs Xijun Wang, Alice Lucas, Santiago Lopez-Tapia, Xinyi Wu, Rafael Molina, Aggelos K. Katsaggelos IEEE ICASSP (Oral), 2019 PDF

Motion Blur Removal

Motion artifact reduction in abdominal MRIs using generative adversarial networks with perceptual similarity loss
Yunan Wu¹, Xijun Wang¹, Aggelos K. Katsaggelos (¹Joint first author)
International Symposium on Medical Information Processing and Analysis (Oral), 2021
PDF

Restoration + Recognition

Restore What Matters: Lessons from Joint Restoration and Recognition
Lanqing Guo¹, Xijun Wang¹, Minchul Kim¹ Yu Yuan, Wes Robbins, Xingguang Zhang, Nicholas Chimitt, Stanley H. Chan, Zhangyang Wang, Xiaoming Liu (¹Joint first author)
Under Review

Video Activity Recognition

Avian Activity Classification Using Recurrent Networks to Fuse Videos with Metadata on Imbalanced Datasets
Xijun Wang, Adam Szymanski, Yuki Hamada, Aggelos K. Katsaggelos
ICCAI (Oral), 2024
PDF

Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization
Xijun Wang, Aggelos K. Katsaggelos
Under Review
PDF

Cool sites from Jon Barron's website. Thanks for Leonid Keselman's Jekyll template.