SIG Seminar: “Uncertainty-Driven Geometry Reconstruction and Understanding”
Zoom - Email CIS for link cherylh@cis.upenn.eduChoosing suitable data representations is one of the most critical topics when installing machine learning on 3D data. This talk discusses several recent works on utilizing uncertainty as a lens to develop suitable data representations and formulations for geometry reconstruction and understanding. We will discuss both theoretical results and applications in multi-scan registration, pose estimation, […]