JaeSeong Kim

Mobile Computational Photography
Image Quality • ISP Tuning • Sensor Design

I am a recent M.Sc. graduate in Electrical & Electronics Engineering from Tel Aviv University, where I also completed my B.Sc. I specialize in computer vision and computational imaging, with research focused on polarization-based face anti-spoofing and computational photography for consumer cameras.

During my Master's, I worked with Prof. David Mendlovic on novel polarization camera designs, resulting in a first-author IEEE Sensors Journal paper and a related patent (WO 2024/161329). Previously, I was an Image Quality Engineer at Samsung Corephotonics, where I worked on ISP tuning, image quality assessment, and camera-sensor performance evaluation.

My research interests lie in computational photography, camera-sensor innovation, and imaging algorithms that enhance everyday devices. I am currently seeking PhD opportunities to advance these fields.

Email Google Scholar LinkedIn GitHub CV
JaeSeong Kim

Scroll Down

News

Aug 2025

🎉Paper published! Our work on sparse polarization pixels for face anti-spoofing has been published in IEEE Sensors Journal!

Aug 2024

📄Patent published! Our invention on compact face identification polarization cameras has been published as WO2024161329A1.

Research

Polarization Research

On the Effectiveness of Sparse Linear Polarization Pixels for Face Anti-Spoofing

JaeSeong Kim, Abraham Pelz, Michael Scherer, David Mendlovic
IEEE Sensors Journal, 2025
Investigation of sparse linear polarization pixel architectures for face anti-spoofing in mobile devices, demonstrating effective liveness detection with minimal sensor modifications.
Project Page Paper

Patent

Patent

Sensors, systems and methods for compact face identification polarization cameras

Michael Scherer, JaeSeong Kim
WO 2024/161329, 2024
Novel sensor architecture and imaging system design for polarization-based face identification in compact form factors suitable for mobile devices.
Patent

Projects

FOV Tool

FOV Measurement Tool

Automated tool for computing camera Field of View metrics—horizontal, vertical, and diagonal angles—using reference chart dimensions and measured distance for accurate lens specification.
GitHub
EIS Tool

EIS & Motion Blur Measurement Tool

Automated tool that analyzes video of a camera oscillating in front of a test chart to quantify Electronic Image Stabilization (EIS) angular correction and motion blur magnitude, providing objective assessment of camera stabilization performance.
GitHub
Crime Analysis

Crime Analysis with Computer Vision

Intelligent surveillance system that classifies ten types of crime from video footage using Convolutional Neural Networks. The model employs a two-stage architecture with anomaly detection followed by skeletal movement pattern analysis.
GitHub Article