arrow
返回

Regional dynamic point cloud completion network

delete2024-10-01
delete0
PRE
AI
L
Liping Zhu
Y
Yixuan Yang *
K
Kai Liu
S
Silin Wu
B
Bingyao Wang
C
Chang, Xianxiang
DOI:10.1016/j.patrec.2024.10.017delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Point cloud completion network often encodes points into a global feature vector, then predicts the complete point cloud through the vector generation process. However, this method may not accurately capture complex shapes, as global feature vectors struggle to recover their detailed structure. In this paper, we present a novel shape completion network, namely RD-Net, that innovatively focuses on the interaction of information between points to provide both local and global information for generating fine-grained complete shape. Specifically, we propose a stored iteration-based method for point cloud sampling that quickly captures representative points within the point cloud. Subsequently, in order to better predict the shape and structure of the missing part, we design an iterative edge-convolution module. It uses a CNN-like hierarchy for feature extraction and learning context information. Moreover, we design a two-stage reconstruction process for latent vector decoding. We first employ a feature-points-based multi-scale generating decoder to estimate the missing point cloud hierarchically. This is followed by a self-attention mechanism that refines the generated shape and effectively generates structural details. By combining these innovations, RD-Net achieves a 2% reduction in CD error compared to the state-of-the-art method on the ShapeNet-part dataset.
Keyword:
Point cloud shape completion
Deep learning
Edge convolution
Stored distance iteration
Self-attention mechanism

期刊

Pattern Recognition Letters 封面图
Pattern Recognition Letters
IF:
3.3
论文数:
8.0K
被引数:
1.6W

机构

C
china university of petroleum
学者数:
4.1W
论文数: 2.7W
被引数: 30
引用论文

引用论文

Learnable Chamfer Distance for point cloud reconstruction用于点云重建的可学习倒角距离
err2024-02-01
err4
errOAAI
errHuang, Tianxin; Liu, Qingyao; Zhao, Xiangrui; Chen, Jun; Liu, Yong
err分享
err收藏
Towards point cloud completion: Point Rank Sampling and Cross-Cascade Graph CNN
err2021-10-01
err23
PREAI
errZhu, Liping; Wang, Bingyao; Tian, Gangyi; Wang, Wenjie; Li, Chengyang
err分享
err收藏
Molecular Basis of Filamin A-FilGAP Interaction and Its Impairment in Congenital Disorders Associated with Filamin A Mutations
err2009-03-18
err0
errOAAI
errFumihiko Nakamura; Outi Heikkinen; Olli T. Pentikäinen; Teresia M. Osborn; Karen E. Kasza; David A. Weitz; Olga Kupiainen; Perttu Permi; Ilkka Kilpeläinen; Jari Ylänne; John H. Hartwig; Thomas P. Stossel
err分享
err收藏
err分享
err收藏
Two-stage feature distribution rectification for few-shot point cloud semantic segmentation
err2024-01-01
err2
PREAI
errWang, Tichao; Hao, Fusheng; Cui, Guosheng; Wu, Fuxiang; Yang, Mengjie; Zhang, Qieshi; Cheng, Jun
err分享
err收藏
Thermal activation of methane by vanadium boride cluster cations VBn+ (n = 3–6)
err2018-01-01
err0
PREAI
errQiang Chen; Yan-Xia Zhao; Li-Xue Jiang; Hai-Fang Li; Jiao-Jiao Chen; Ting Zhang; Qing-Yu Liu; Sheng-Gui He
err分享
err收藏
A group lasso based sparse KNN classifier
err2020-03-01
err15
PREAI
errZheng, Shuai; Ding, Chris
err分享
err收藏
学者 查看更多内容