SGP 2020 Graduate School: Deep Learning for Geometric Data

Niloy Mitra and Paul Guerrero More details at In computer graphics, many traditional problems are now better handled by deep-learning-based data-driven methods. In an increasing variety of problem settings, deep networks are state-of-the-art, beating dedicated hand-crafted methods by significant margins. After reviewing relevant background from the regular imaging domain, in this tutorial, we will discuss the state-of-the-art in terms of geometry and topology synthes