I am a Ph.D. student at Fei Xia Research Lab @ UC, Irvine, with research interests in Computational Imaging, particularly in imaging through scattering media and signal process. I have earned both my Bachelor’s and Master’s degrees from Huazhong University of Science and Technology (HUST) and Xi’an Jiaotong University (XJTU), respectively. I have previously interned and worked full-time at OPPO and VIVO as Machine Learning Engineer, where I was responsible for developing AI denoising models for smartphones.
📖 Educations
- 2025.09 - Present, Ph.D Student, Electrical Engineering and Computer Sciences, UC Irvine
. Advisor: Prof. Fei Xia - 2021.09 - 2024.06, Master of Engineering, Electronic Information, Xi’an Jiaotong Univerisity
. Advisor: Prof. Jianbin Liu - 2017.09 - 2021.06, Bachelor of Engineering, Electrical Engineering and Automation, Huazhong University of Science and Technology
💻 Experience
- 2024.07 - 2025.04, Machine Learning Engineer, YLab, OPPO Research Institute
, China. Advisor: Prof. Lei Zhang - 2023.03 - 2023.05, Machine Learning Intern, VIVO Dept. of Image Effect
, China
🔥 News
- 2026.04, One of our papers has been accepted by the journal Advanced Photonics.
- 2025.11, Receiving the competitive Henry Samueli Endowed fellowship for Spring 2026.
- 2025.03, Joining Fei Xia Research Lab as a Ph.D student in Fall 2025.
- 2024.07, Joining YLab in OPPO Research Institute as an Image Algorithm Engineer.
📝 Selected Publications
Adv. Photonics 2026
NeOTF: Guidestar-free neural representation for broadband dynamic imaging through scattering
Y Sun and F Xia.
- We introduce NeOTF, a framework that learns an implicit neural representation of the OTF. By applying multi-frame speckle intensities and Fourier-domain prior, NeOTF robustly retrieves the system’s OTF with high fidelity and efficiency.
- [OLEN 2023] Non-invasive color imaging through scattering medium under broadband illumination, Yunong Sun, et al.
📦 Selected Repositories
Github
Open-AISP: An open-source AI-ISP pipeline framework for beginners
- A beginner-friendly and toy-level AI-ISP pipeline framework covering realistic raw image degradation simulation, neural ISP pipeline reconstruction, and image post-enhancement with generative prior.
- Current modules include raw simulation raw-sim and multi-frame joint denoising/demosaicing (JDD), with multi-frame HDR fusion (HDR-fusion), learning-based tonemapping(AITM), and diffusion-based post-enhancement (DiffIPE) on the roadmap.
