I am a Staff Engineer at Samsung Electronics (DS Division, AX/PI Center), developing agentic AI for semiconductor manufacturing.
I received my Ph.D. from the Computer Vision Lab, Seoul National University, advised by Prof. Kyoung Mu Lee. During my Ph.D., I worked on application-oriented image restoration in two directions: task-driven image restoration, which tailors restoration models to specific high-level vision tasks, and real-world image restoration, which handles realistically degraded inputs beyond synthetic assumptions. I remain broadly interested in foundation models, such as diffusion and vision-language models, as priors and tools.
You can download my CV here 📄.
🔥 News
- 2026.09: 💼 Joined Samsung Electronics as a Staff Engineer!
- 2026.09: 🎉🎉 One paper got accepted to ACCV 2026!
- 2026.08: 🎓 Completed my Ph.D. at Seoul National University!
- 2026.07: 🎉🎉 One paper got accepted to ECCV 2026!
📝 Publications
Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priors (First author) Jaeha Kim and Kyoung Mu Lee
- Proposing a deterministic one-step adaptation for stable task-driven restoration.
- Code
Learning to Corrupt for Better Restoration (Author) Joonkyu Park, Wooseok Lee, Jaeha Kim, Sehoon Kim, Bokyeung Lee, and Kyoung Mu Lee
- Proposing input-aware corruption modeling to improve perceptual quality in diffusion-based image restoration.
Exploiting Diffusion Prior for Task-driven Image Restoration (First author) Jaeha Kim, Junghun Oh, and Kyoung Mu Lee
- Task-driven diffusion-based image restoration for improved high-level vision tasks.
- Code
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss (First author) Jaeha Kim, Junghun Oh, and Kyoung Mu Lee
- A task-driven super-resolution framework for image recognition.
- Code
Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding (Co-first author) Yeoung Uk Oh*, JoonKyu Park*, Jaeha Kim*, Gyeongsik Moon, Kyoung Mu Lee
- A new practical benchmark for 3D hand pose estimation under blur.
- Code
Toward Real-World Super-Resolution via Adaptive Downsampling Models (Co-first author) Sanghyun Son*, Jaeha Kim*, Wei-Sheng Lai, Ming-Hsuan Yang, Kyoung Mu Lee
🎖 Honors and Awards
- 2025.06 Outstanding Reviewer (Top 5%), CVPR 2025.
- 2019.02 National Scholarship (Undergraduate), Korea Student Aid Foundation.
📖 Educations
- 2019.09 - 2026.08, Ph.D. in Electrical and Computer Engineering, Seoul National University, Seoul, Korea.
- 2015.03 - 2019.02, B.S. in Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea.
- 2013.03 - 2015.02, Incheon Science High School, Incheon, Korea.