Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

12/23/2019
by   Mingye Xu, et al.
0

In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we propose Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations. Compared with previous 3D point CNNs which perform convolution on nearby points, GS-Net can aggregate point features in a more global way. Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space. This design allows GS-Net to efficiently capture both local and holistic geometric features such as symmetry, curvature, convexity and connectivity. Theoretically, we show the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet Part. Experiments demonstrate that GS-Net achieves the state-of-the-art performances on major datasets, 93.3 more robust to geometric transformations.

READ FULL TEXT
research
09/27/2022

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

Successful point cloud registration relies on accurate correspondences e...
research
11/01/2019

Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology

Point cloud analysis is a basic task in 3D computer vision, which attrac...
research
01/07/2021

Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition

Point cloud based retrieval for place recognition is still a challenging...
research
11/30/2021

Robust Partial-to-Partial Point Cloud Registration in a Full Range

Point cloud registration for 3D objects is very challenging due to spars...
research
12/22/2020

Geometric robust descriptor for 3D point cloud

We propose rotation robust and density robust local geometric descriptor...
research
08/30/2018

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

We present PPF-FoldNet for unsupervised learning of 3D local descriptors...
research
05/02/2022

APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification

Point-cloud-based 3D classification task involves aggregating features f...

Please sign up or login with your details

Forgot password? Click here to reset