Mingi Lee
I'm a Ph.D. student in the 3D Vision Lab at Seoul National University, advised by Prof. Young Min Kim. My research lies at the intersection of structured 3D geometry(e.g. CAD) and generative modeling, with a focus on bridging functional design and geometric learning. I aim to develop structure-aware, editable geometric systems that are grounded in real-world usability, by integrating geometric reasoning, differentiable physics, and generative models. I recently spent time as a visiting researcher for collaborations at the User Interface Research Group at the University of Tokyo. Beyond research, I love to boulder🧗, ski⛷, snorkel🤿. Feel free to reach out to me for any kinds of discussions or collaborations from research to a climbing session.🙇♂️
Contact: Email, LinkedInPublications
BrepDiff: Single-stage B-rep Diffusion Model
Mingi Lee*, Dongsu Zhang*, Clément Jambon*, Young Min Kim
SIGGRAPH 2025
BrepDiff is a simple, single-stage diffusion model for generating Boundary Representations (B-reps). It generates B-reps by denoising point-based face samples with a dedicated noise schedule. Unlike multi-stage methods, BrepDiff enables intuitive, editable geometry creation, including completion, merging, and interpolation, while achieving competitive performance on unconditional generation.
