Learning to Vary 3D Models for Universally Accessible 3D Content Creation

Explore cutting-edge research on 3D model generation and deformation in this 55-minute seminar presented by Mikaela Angelina Uy, a Stanford University Ph.D. student. Dive into innovative approaches for making 3D content creation universally accessible, including a target-centric method for retrieving and deforming existing CAD models to fit target images or scans. Learn about techniques for generating high-quality 3D shapes that rival artist-created models in fidelity and detail. Discover ongoing efforts to incorporate user interaction and control in shape deformation through the prediction of source-dependent deformation handles. Gain insights into the future of automated 3D content creation and its potential to revolutionize how we digitize and represent the physical world.