Anisotropic Gauss Reconstruction for Unoriented Point Clouds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911889113481216 |
|---|---|
| author | Ma, Yueji Xiao, Dong Shi, Zuoqiang Wang, Bin |
| author_facet | Ma, Yueji Xiao, Dong Shi, Zuoqiang Wang, Bin |
| contents | Unoriented surface reconstructions based on the Gauss formula have attracted much attention due to their elegant mathematical formulation and excellent performance. However, the isotropic characteristics of the formulation limit their capacity to leverage the anisotropic information within the point cloud. In this work, we propose a novel anisotropic formulation by introducing a convection term in the original Laplace operator. By choosing different velocity vectors, the anisotropic feature can be exploited to construct more effective linear equations. Moreover, an adaptive selection strategy is introduced for the velocity vector to further enhance the orientation and reconstruction performance of thin structures. Extensive experiments demonstrate that our method achieves state-of-the-art performance and manages various challenging situations, especially for models with thin structures or small holes. The source code will be released on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17193 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Anisotropic Gauss Reconstruction for Unoriented Point Clouds Ma, Yueji Xiao, Dong Shi, Zuoqiang Wang, Bin Graphics Unoriented surface reconstructions based on the Gauss formula have attracted much attention due to their elegant mathematical formulation and excellent performance. However, the isotropic characteristics of the formulation limit their capacity to leverage the anisotropic information within the point cloud. In this work, we propose a novel anisotropic formulation by introducing a convection term in the original Laplace operator. By choosing different velocity vectors, the anisotropic feature can be exploited to construct more effective linear equations. Moreover, an adaptive selection strategy is introduced for the velocity vector to further enhance the orientation and reconstruction performance of thin structures. Extensive experiments demonstrate that our method achieves state-of-the-art performance and manages various challenging situations, especially for models with thin structures or small holes. The source code will be released on GitHub. |
| title | Anisotropic Gauss Reconstruction for Unoriented Point Clouds |
| topic | Graphics |
| url | https://arxiv.org/abs/2405.17193 |