.png){kind=icon}
返回
Learnable Point Cloud Sampling Considering Seed Point for Neural Surface Reconstruction
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3518620.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reconstruction of surfaces from point clouds is essential in numerous practical applications. An approach in which neural fields are trained as surface representations from point clouds has garnered significant interest in recent years. However, these techniques present scalability issues to large scenes since they are limited in the size of point clouds that can be processed. This work proposes a learnable point cloud sampling designed to address the scalability issues. We introduce a sampling network that considers a seed point acting as the origin to sample points from a part of the scene. The seed point is one of the input points that is selected in a spatially uniform manner. This prompts a surface reconstruction network to learn the detailed geometry on partial regions of the scene. We also propose a training pipeline based on point cloud splitting and merging to avoid an increase in the memory footprint. We jointly train the sampling network and surface reconstruction network using a task loss to optimize the sampling network for the surface reconstruction task. Experimental results on scene-level datasets captured from real-world environments demonstrate that our method performs better than state-of-the-art methods in surface reconstruction.
Keyword:
Point cloud compression
Surface reconstruction
Feature extraction
Training
Scalability
Three-dimensional displays
Geometry
Decoding
Surface treatment
Shape
Point cloud sampling
surface reconstruction
neural fields
seed point
local geometry
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Changes in oestrous cyclicity following olfactory bulbectomy in post-pubertal pigs.png)
Reproduction
OAAI
ReproductionIF0
OAAI分享收藏分享收藏分享收藏
查看更多内容