.png){kind=icon}
返回
Improving point cloud classification and segmentation via parametric veronese mapping
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109784.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning based 3D point cloud classification and segmentation has achieved remarkable success. Existing methods are usually implemented in the original space with 3D coordinates as inputs. However, we find that point networks taking only information of first-order coordinates hardly learn geometric features of higher order, such as point cloud normals or poses. In this study, we propose to map the input point clouds into a non-linear space to facilitate networks learning and leveraging high-order features. Firstly, we design the Parametric Veronese Mapping (PVM) function which automatically learns to map point clouds into a non-linear space. As a result, the mapped point clouds are enriched with high-order elements and maintain the basic point set properties as in the original 3D space. We can then exploit existing networks to learn high-order features from mapped point clouds. Secondly, we contribute a two-stage transformation learning module that modifies the previous one-stage module to better leverage high-order features for aligning point clouds in the projective space. Finally, an interaction module is designed to learn more discriminative features by aggregating information from both the original and projective space. Extensive experiments demonstrate that our method successfully improves the ability of most existing networks to learn high-order features and thus contributing to more accurate classification and segmentation. Moreover, the resulting models show stronger robustness to affine transformations and real-world perturbations.
Keyword:
3D Point cloud
Deep learning
Non-linear space mapping
Shape classification
Part segmentation
Semantic segmentation
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
KDD: A kernel density based descriptor for 3D point cloudsKDD: 一种基于核密度的三维点云描述符.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Connectivity-based convolutional neural network for classifying point cloudsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Continuous conditional random field convolution for point cloud segmentationPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏3D-CenterNet: 3D object detection network for point clouds with center estimation priority *3D-CenterNet: 具有中心估计优先级的点云3D物体检测网络 *PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏
查看更多内容