GraVoS: Voxel Selection for 3D Point-Cloud Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910367381192704 |
|---|---|
| author | Shrout, Oren Ben-Shabat, Yizhak Tal, Ayellet |
| author_facet | Shrout, Oren Ben-Shabat, Yizhak Tal, Ayellet |
| contents | 3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to add ground-truth objects from other scenes. Differently, we propose to modify the scenes by removing elements (voxels), rather than adding ones. Our approach selects the "meaningful" voxels, in a manner that addresses both types of dataset imbalance. The approach is general and can be applied to any voxel-based detector, yet the meaningfulness of a voxel is network-dependent. Our voxel selection is shown to improve the performance of several prominent 3D detection methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_08780 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | GraVoS: Voxel Selection for 3D Point-Cloud Detection Shrout, Oren Ben-Shabat, Yizhak Tal, Ayellet Computer Vision and Pattern Recognition 3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to add ground-truth objects from other scenes. Differently, we propose to modify the scenes by removing elements (voxels), rather than adding ones. Our approach selects the "meaningful" voxels, in a manner that addresses both types of dataset imbalance. The approach is general and can be applied to any voxel-based detector, yet the meaningfulness of a voxel is network-dependent. Our voxel selection is shown to improve the performance of several prominent 3D detection methods. |
| title | GraVoS: Voxel Selection for 3D Point-Cloud Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2208.08780 |