Variational Autoencoding of Dental Point Clouds

TL;DR

This paper introduces a probabilistic autoencoder for dental point clouds, leveraging a new dataset and achieving state-of-the-art results in dental shape reconstruction, interpolation, and generation.

Contribution

The paper presents VF-Net, a novel variational autoencoder for point clouds that improves probabilistic modeling and computational efficiency in dental shape analysis.

Findings

Lower reconstruction error in dental shape tasks

State-of-the-art dental sample generation

Effective shape interpolation and representation learning

Abstract

Digital dentistry has made significant advancements, yet numerous challenges remain. This paper introduces the FDI 16 dataset, an extensive collection of tooth meshes and point clouds. Additionally, we present a novel approach: Variational FoldingNet (VF-Net), a fully probabilistic variational autoencoder for point clouds. Notably, prior latent variable models for point clouds lack a one-to-one correspondence between input and output points. Instead, they rely on optimizing Chamfer distances, a metric that lacks a normalized distributional counterpart, rendering it unsuitable for probabilistic modeling. We replace the explicit minimization of Chamfer distances with a suitable encoder, increasing computational efficiency while simplifying the probabilistic extension. This allows for straightforward application in various tasks, including mesh generation, shape completion, and representation learning. Empirically, we provide evidence of lower reconstruction error in dental reconstruction and interpolation, showcasing state-of-the-art performance in dental sample generation while identifying valuable latent representations