.png){kind=icon}
返回
Point cloud completion network for 3D shapes with morphologically diverse structures
.png){kind=icon}
OA
AI
DOI：10.1007/s40747-023-01325-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Point cloud completion is a challenging task that involves predicting missing parts in incomplete 3D shapes. While existing strategies have shown effectiveness on point cloud datasets with regular shapes and continuous surfaces, they struggled to manage the morphologically diverse structures commonly encountered in real-world scenarios. This research proposed a new point cloud completion method, called SegCompletion, to derive complete 3D geometries from a partial shape with different structures and discontinuous surfaces. To achieve this, morphological segmentation was introduced before point cloud completion by deep hierarchical feature learning on point sets, and thus, the complex morphological structure was segmented into regular shapes and continuous surfaces. Additionally, each instance of a point cloud that belonged to the same type of feature could also be effectively identified using HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise). Furthermore, the multiscale generative network achieved sophisticated patching of missing point clouds under the same geometric feature based on feature points. To compensate for the variance in the mean distances between the centers of the patches and their closest neighbors, a simple yet effective uniform loss was utilized. A number of experiments on ShapeNet and Pheno4D datasets have shown the performance of SegCompletion on public datasets. Moreover, the contribution of SegCompletion to our dataset (Cotton3D) was discussed. The experimental results demonstrated that SegCompletion performed better than existing methods reported in the literature.
Keyword:
Morphologically diverse structures
Morphological segmentation
Uniform loss
Point cloud completion
SegCompletion
期刊
IF:
4.6
论文数:
2.1K
被引数:
6.6K
机构
引用论文
Hybrid image encryption algorithm based on 3D chaotic system and choquet fuzzy integral基于三维混沌系统和choquet模糊积分的混合图像加密算法
PREAI
分享收藏Dynamic Measurement of Portos Tomato Seedling Growth Using the Kinect 2.0 Sensor.png)
AGRICULTURE-BASELOAAI
AGRICULTURE-BASELIF3.6
OAAI分享收藏LGAN: Lung segmentation in CT scans using generative adversarial networkLGAN: 使用生成对抗网络在ct扫描中进行肺分割
OAAI
OAAI分享收藏
查看更多内容