About Me

Introduction

    My name is Yu Yuan (袁煜), a second-year PhD student at Purdue ECE, under the supervision of Prof. Stanley H. Chan. Prior to this, I obtained my master and bachelor degree in Aerospace Engineering from Shanghai Jiao Tong University in 2023 and 2020 respectively.

   My research interests encompass computer vision and machine learning, with a particular emphasis on generative models and computational photography. My long-term goal is to create a physically consistent generative world.

Selected Research

Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis Yu Yuan, Xijun Wang, Yichen Sheng, Prateek Chennuri, Xingguang Zhang, Stanley Chan CVPR 2025 Highlight & CVPR 2025 Demo > proj ｜ > arXiv ｜ > code ｜ > demo ｜ > dataset

Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation Xingguang Zhang, Nicholas Chimitt, Xijun Wang, Yu Yuan, Stanley Chan CVPR 2025 Highlight > proj ｜ > arXiv ｜ > code

NewtonGen: Physics-consistent Text-to-Video Generation via Neural Newtonian Dynamics Yu Yuan, Xijun Wang, Zeeshan Nadir, Bole Ma, Stanley Chan Under Review > arXiv

Beyond Clean Pixels: Interdisciplinary Lessons from Turbulent Long-Range Face Recognition Lanqing Guo1, Xijun Wang1, Minchul Kim1, Yu Yuan, Wes Robbins, Xingguang Zhang, Stanley H. Chan, Zhangyang Wang, Xiaoming Liu Under Review > arXiv

Personalized Generative Low-light Image Denoising and Enhancement Xijun Wang, Prateek Chennuri, Yu Yuan, Bole Ma, Xingguang Zhang, Stanley Chan Under Review > proj ｜ > arXiv

iHDR: Iterative HDR Imaging with Arbitrary Number of Inputs Yu Yuan, Yiheng Chi, Xingguang Zhang, Stanley Chan ICIP 2025 > arXiv

Astrophotography Turbulence Mitigation via Generative Models Joonyeoup Kim, Yu Yuan, Xingguang Zhang, Xijun Wang, Stanley Chan ICIP 2025 > proj ｜ > arXiv

RCMixer: Radar-camera Fusion Based on Vision Transformer for Robust Object Detection Lindong Wang, Hongya Tuo, Yu Yuan, Henry Leung, Zhongliang Jing Journal of Visual Communication and Image Representation > doi

Learning to Kindle the Starlight Yu Yuan, Jiaqi Wu, Lindong Wang, Zhongliang Jing, Henry Leung, Shuyuan Zhu, Han Pan Rejected by CVPR 2023 > arXiv ｜ > code ｜ > dataset

Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attention Yu Yuan, Jiaqi Wu, Zhongliang Jing, Henry Leung, Han Pan > arXiv ｜ > code

Projects

On-going Projects

1. Physically-driven Visual Content Generation
2. Generative Restoration

Previous Projects

1. Generative Astronomical Image Restoration Through Atmospheric Turbulence (2025)
2. Video Restoration Classifier (2024)
3. A Underwater Binocular Multi-exposure Imaging System (2022)
4. Ultra-wideband-based Cooperative Multi-UAV Positioning Technology (2021)
5. A Modular Custom Aviation Model Design for Tyros (2020)

Patent

基于自主水下机器人惯导与超短基线定位传感器的轨迹解算与配准方法，中国发明专利 CN 114993313 B （2025）

Misc.

1. Angler: Got the Prize named Fish of the Year ('Cause I Got the Biggest One of Goldeye Fish in Indiana State, 2023)
2. Landscape Photographer: One Milky Way Photo Accepted to Astronomy Picture of the Day in Nightchina (2021)
3. Mountaineer: Arrived at the 2nd Peak of Mount Siguniang (5276m, 2020)
4. Aviation Enthusiast: Experienced More Than 40 Types of Manned Aircrafts, also with 8 Years of Drone Flying Experience
5. I’m always happy to collaborate and make new friends. Feel free to reach out if you share similar interests! :
   Email | Linkedin | Google Scholar | Github | Flickr