About Me

I'm a ML Engineer at Beeble, where I optimize the de-rendering algorithm in SwitchLight for AI virtual production. I'm interested in controllable content creation and editing with enhanced visual consistency, empowering general users to generate high-quality visuals for storytelling with a streamlined workflow.

Previously, I completed MS degree at POSTECH's Computer Graphics Lab under the supervision of Prof. Seung-Hwan Baek. My graduate research focused on comprehensive analysis and modeling of light properties [NeSpoF, SpoDataset, Spectro-polarimetric BRDF].

Work Experience

Beeble

Apr. 2024 - Present
ML Engineer

> Contribute to SwitchLight for more effective relighting and background compositing in AI virtual production
> Optimize the de-rendering algorithm for accurate PBR materials and depth extraction from a single image
> Develop a realistic multi-human generation and synthetic dataset rendering pipeline with virtual light stage

Publications

image
Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset
Yujin Jeon*, Eunsue Choi*, Youngchan Kim, Yunseong Moon, Khalid Omer, Felix Heide, Seung-Hwan Baek
CVPR 2024 (highlight)
> Real-world datasets that include both linear and circular polarization acroos multiple spectral channels
image
Neural Spectro-polarimetric Fields
Youngchan Kim, Wonjoon Jin, Sunghyun Cho, Seung-Hwan Baek
SIGGRAPH Asia 2023
> Neural representation that models the physically-valid hyperspectral Stokes vector at given position and direction

Projects

image
AMPER(Aim-Measure-Predict-Evaluate-Recommend): The Paradigm of Digital Me
> Implement a general Digital Me algorithm to manage the individual's state and provide recommendations