Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2201.09263 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917604889722880 |
|---|---|
| author | Novello, Tiago Schardong, Guilherme Schirmer, Luiz da Silva, Vinicius Lopes, Helio Velho, Luiz |
| author_facet | Novello, Tiago Schardong, Guilherme Schirmer, Luiz da Silva, Vinicius Lopes, Helio Velho, Luiz |
| contents | We introduce a neural implicit framework that exploits the differentiable properties of neural networks and the discrete geometry of point-sampled surfaces to approximate them as the level sets of neural implicit functions.
To train a neural implicit function, we propose a loss functional that approximates a signed distance function, and allows terms with high-order derivatives, such as the alignment between the principal directions of curvature, to learn more geometric details. During training, we consider a non-uniform sampling strategy based on the curvatures of the point-sampled surface to prioritize points with more geometric details. This sampling implies faster learning while preserving geometric accuracy when compared with previous approaches.
We also use the analytical derivatives of a neural implicit function to estimate the differential measures of the underlying point-sampled surface. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2201_09263 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Exploring Differential Geometry in Neural Implicits Novello, Tiago Schardong, Guilherme Schirmer, Luiz da Silva, Vinicius Lopes, Helio Velho, Luiz Graphics Machine Learning We introduce a neural implicit framework that exploits the differentiable properties of neural networks and the discrete geometry of point-sampled surfaces to approximate them as the level sets of neural implicit functions. To train a neural implicit function, we propose a loss functional that approximates a signed distance function, and allows terms with high-order derivatives, such as the alignment between the principal directions of curvature, to learn more geometric details. During training, we consider a non-uniform sampling strategy based on the curvatures of the point-sampled surface to prioritize points with more geometric details. This sampling implies faster learning while preserving geometric accuracy when compared with previous approaches. We also use the analytical derivatives of a neural implicit function to estimate the differential measures of the underlying point-sampled surface. |
| title | Exploring Differential Geometry in Neural Implicits |
| topic | Graphics Machine Learning |
| url | https://arxiv.org/abs/2201.09263 |