I’m a Ph.D. student in Computer Science and Engineering at Seoul National University, advised by Professor Gunhee Kim in the Vision & Learning Lab.
I explore how generative models can be controlled to follow user intent while respecting physical and semantic scene constraints. A particular focus is keeping lighting effects consistent with the geometry, materials, and light sources that produce them.
My work spans inverse rendering, neural rendering, and diffusion-based object compositing. Building on this experience, I’m interested in how physical modeling and the design of data and supervision can help models learn such control—and how to evaluate it.
I did my undergraduate degree at Chung-Ang University, graduating as valedictorian of the College of Engineering.
