About me

I'm Wooseok Lee, a Ph.D. student in Electrical and Computer Engineering (ECE) at Seoul National University, supervised by Prof. Kyoung Mu Lee. My research focuses on low-level image restoration, with a particular emphasis on practical real-world image denoising.

Especially, I study self-supervised denoising methods that recover clean images from noisy observations without ground-truth (GT) clean images. I aim to develop reliable approaches that can be trained directly on real-world noisy data, where collecting paired clean targets is often impractical.

Papers

Learning to Corrupt for Better Restoration

Joonkyu Park, Wooseok Lee, Jaeha Kim, Sehoon Kim, Bokyeung Lee, Kyoung Mu Lee

ECCV, 2026

Research projects

Self-supervised Raw Real-world Image Denoising

Hanwha Techwin

Self-supervised Scanning Electron Microscope (SEM) Image Denoising

Samsung Electronics (Semiconductor R&D Center)

Tunable Software Image Signal Processing

Samsung Electronics (SAIT)

Camera Image Restoration using Large AI Models

Samsung Electronics (MX)

AI-driven Optimal Formulation Technology to Enhance Zinc Oxide Yield

Taekyung SBC

Contact