Variational Autoencoding of Dental Point Clouds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910578992218112 |
|---|---|
| author | Ye, Johan Ziruo Ørkild, Thomas Søndergaard, Peter Lempel Hauberg, Søren |
| author_facet | Ye, Johan Ziruo Ørkild, Thomas Søndergaard, Peter Lempel Hauberg, Søren |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_10895 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Variational Autoencoding of Dental Point Clouds Ye, Johan Ziruo Ørkild, Thomas Søndergaard, Peter Lempel Hauberg, Søren Computer Vision and Pattern Recognition Machine Learning 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 |
| title | Variational Autoencoding of Dental Point Clouds |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2307.10895 |