Geometric deep learning for non-rigid shapes: From theory to practice
Date:
In this talk, we present first the inherent challenges of deep learning on 3D surfaces, in the context of shape analysis. We present the early approaches to tackle this problem and explain why they were failing. We then present two modern architectures: PointNet, a key component in many modern point cloud architecture, and DiffusionNet, a backbone that is still used in state-of-the-art shape matching approaches. We also discuss the need to regularize latent spaces of shapes to reproduce faithful interpolation in the latent space.