About Me
I'm a Machine Learning Engineer at Beeble AI, where I contribute to developmet and optimization AI/ML pipeline to extract visual scene data for relighting, compositing, and 3D integration. I completed my Master's degree at POSTECH Computer Graphics Lab under the supervision of Prof. Seung-Hwan Baek, focusing on comprehensive analysis and modeling of light properties [NeSpoF, SpoDataset, hpBRDF].
Work Experience
Provide virtual lighting solutions that transform 2D footage into 3D relightable PBR assets and generate HDRI harmonized with virtual background
Key Responsibilities
- Optimize and refine AI models (e.g., segmentation, depth estimation, camera tracking) for pipeline integration
- Train de-rendering and text-to-image diffusion models using a custom-built synthetic data generation pipeline
- Develop 3D web editor and Blender add-on that supports post-processing with PBR maps extracted from shots
Publications
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)
Neural Spectro-polarimetric Fields
Youngchan Kim, Wonjoon Jin, Sunghyun Cho, Seung-Hwan Baek
SIGGRAPH Asia, 2023
Projects
MEDIVATION
All-in-one Health Platform for Self-diagnosis and Medication Management
- Develop AI algorithm that evaluates individual health status and recommends personalized medications
MIXPRESET
Worldwide Mixing and Mastering Platform
- Develop full-stack web platform for music creators to streamline mixing workflow through preset exchange
AMPER
Minimally Domain-dependent Privacy-preserving Digital Me Algorithms
- Develop transformer-based Digital Me algorithm to manage individual's state and provide recommendation