Abstract: Geometry can make AI approaches more accurate, efficient and controllable. In this talk, we cover three contributions that demonstrate this. The first is DeltaConv, a building block for CNNs on curved surfaces. DeltaConv works directly on the surface, rather than in 3D space. That means the networks can be more efficient and robust to deformations of the shape, but it complicates learning directional information, because there is no global coordinate system. We solve this by learning anisotropic operators as combinations of coordinate-independent operators. The second contribution concerns empirical uncertainty for appearance capture. We show how to quantify this uncertainty and how uncertainty can be used to improve data capture and use the strengths of generative AI in a targeted way. The third contribution deals with enforcing constraints in generative methods, specifically in mesh reconstruction (TetWeave) and stylized vector-image generation. Finally, we will cover how these contributions can improve generative AI approaches of the future.

Speaker Bio: Ruben Wiersma is a postdoctoral researcher in the Interactive Geometry Lab at ETH Zurich and will start as a research scientist at Adobe Research in Paris in June 2026. He obtained his doctorate cum laude at the TU Delft in 2024 and was a research intern at Adobe in 2023. His research in geometry processing and computer graphics has focused on using geometric approaches for machine learning, object capture, and shape analysis. In addition, he has worked on applying techniques from computer graphics to painting analysis in collaboration with art historians and conservators. Outside of research, Ruben enjoys making music, creating short films and tinkering with Blender, and going outdoors.