Diffusion-based Real-World Super-Resolution
Adapting pretrained diffusion models to real-world super-resolution with degradation-aware representations and one-step restoration.
View project →PhD candidate · Computer vision · Taiwan
翁祥恩 (Shyang) — I build practical vision systems for images that are difficult to see, understand, or use.
Image restoration · Low-light enhancement · Object detection
Currently a PhD candidate in Computer Science at NYCU, I hold dual Master's degrees in ECE from UWM and EL from CYCU. My research expertise lies in Image Processing, Pattern Recognition, and Deep Learning, with a focus on Image Restoration and Object Detection. I care about the gap between a promising model and a system that holds up in the real world.
Recover detail, color, and visibility from degraded imagery.
Turn visual signals into reliable, useful information.
Keep models efficient enough for practical environments.
ACM Lab (Applied Computing and Multimedia Lab). Focus on Computer Vision and Deep Learning.
Electrical and Computer Engineering Concentration
GPA: 3.833
Institute of Computer Science and Engineering
GPA: 4.000
Department of Electrical Engineering
GPA: 3.878 (161 total credits)
Certificate of Cross-Disciplinary Program: Intelligent Robotics
Advisor: Prof. Ching-Chun Huang
Collaborating on a MediaTek industry-academic cooperation project, focusing on Super-Resolution, Diffusion Models, and Image Restoration.
Assisted the proposal writing of NSTC Research Project and ITRI industry-academic cooperation project.
Reviewer for IEEE Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, Digital Signal Processing, Scientific Reports and other journals. Full list on the research page.
Advisor: Prof. Shaou-Gang Miaou
Participated in a NSTC Research Project, focusing on Dynamic Illumination Adjustment and Super-Resolution.
Advisor: Prof. Shaou-Gang Miaou
Participated in a NSTC Research Project, focusing on Image Enhancement and Restoration, Lightweight AI for Edge Devices, and Industry Application of Computer Vision.
Instructor: Prof. Hui-Kai Zeng
Course: Modern Physics
Served as a Senator (議代) for the Department Student Council for 4 years.
Certificate of the CYCU Holistic Education
Adapting pretrained diffusion models to real-world super-resolution with degradation-aware representations and one-step restoration.
View project →Developing smart systems to handle extreme lighting variability in real-world environments.
View project →Highly efficient neural networks designed for mobile devices and edge computing.
View project →Selected writing
arXiv preprint · Apr 2026
arXiv preprint · Dec 2025
International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), vol. 39, no. 12 · 2025
Journal of Internet Technology, vol. 26, no. 4, pp. 423-434 · Jul 2025
arXiv preprint · Sep 2024
Signal, Image and Video Processing · Sep 2024
Paper: Reducing Computational Requirements of Image Dehazing Using Super-Resolution Networks
Project: AI Home Assistant – Interactive Stereoscopic Visual Virtual Voice Assistant
書卷獎, Awarded for semesters 109-2 and 110-1.
Project: Deep Learning-Based System for Assessing Learning Effectiveness
Department of Electronic Engineering, Chung Yuan Christian University