Przemyslaw Musialski

My group works at the intersection of geometry, computer graphics, and machine learning. We investigate problems in

geometry processing · shape optimization · digital fabrication · generative AI

Our research combines geometry, computer graphics, and machine learning to generate digital 3D content — shapes, buildings, and fabricable designs — that is not only realistic but usable. Many generative models produce results that merely look plausible; our work instead builds the underlying geometric structure into the model itself: the grammar of a façade, the mathematics of a surface that can be manufactured, the physical constraints a real object must satisfy. This makes generation both controllable and dependable — models a designer can edit and steer, and that hold up in the real world. Increasingly, the same principles extend our work beyond computer graphics into computer vision and the life sciences.