LRC-Net: learning discriminative features on point clouds by encoding local region contexts

DOI10.1016/J.CAGD.2020.101859zbMATH Open1505.94004arXiv2003.08240OpenAlexW3017935107MaRDI QIDQ2180642FDOQ2180642

Authors: Xinhai Liu, Zhizhong Han, Fangzhou Hong, Yu-Shen Liu, Matthias Zwicker 

Publication date: 14 May 2020

Published in: Computer Aided Geometric Design (Search for Journal in Brave)

Abstract: Learning discriminative feature directly on point clouds is still challenging in the understanding of 3D shapes. Recent methods usually partition point clouds into local region sets, and then extract the local region features with fixed-size CNN or MLP, and finally aggregate all individual local features into a global feature using simple max pooling. However, due to the irregularity and sparsity in sampled point clouds, it is hard to encode the fine-grained geometry of local regions and their spatial relationships when only using the fixed-size filters and individual local feature integration, which limit the ability to learn discriminative features. To address this issue, we present a novel Local-Region-Context Network (LRC-Net), to learn discriminative features on point clouds by encoding the fine-grained contexts inside and among local regions simultaneously. LRC-Net consists of two main modules. The first module, named intra-region context encoding, is designed for capturing the geometric correlation inside each local region by novel variable-size convolution filter. The second module, named inter-region context encoding, is proposed for integrating the spatial relationships among local regions based on spatial similarity measures. Experimental results show that LRC-Net is competitive with state-of-the-art methods in shape classification and shape segmentation applications.

Full work available at URL: https://arxiv.org/abs/2003.08240

Recommendations

• Learning point cloud shapes with geometric and topological structures
• EdgeNet: deep metric learning for 3D shapes
• Deep learning-based 3D local feature descriptor from Mercator projections
• NPTC-net: narrow-band parallel transport convolutional neural networks on point clouds
• Jointly learning shape descriptors and their correspondence via deep triplet CNNs

zbMATH Keywords

contextpoint cloudslocal regiongeometric information

Mathematics Subject Classification ID

Numerical smoothing, curve fitting (65D10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cites Work

• Rolling normal filtering for point clouds
• Directional density measure to intrinsically estimate and counteract non-uniformity in point clouds
• Surface reconstruction by parallel and unified particle-based resampling from point clouds
• Unsupervised 3D Local Feature Learning by Circle Convolutional Restricted Boltzmann Machine
• SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention
• BoSCC: Bag of Spatial Context Correlations for Spatially Enhanced 3D Shape Representation
• Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds Using Spatial-Aware Capsules
• 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention Aggregation

Cited In (6)

• Multi-stage point completion network with critical set supervision
• Deep learning-based 3D local feature descriptor from Mercator projections
• D-net: learning for distinctive point clouds by self-attentive point searching and learnable feature fusion
• Learning point cloud shapes with geometric and topological structures
• NPTC-net: narrow-band parallel transport convolutional neural networks on point clouds
• PointeNet: a lightweight framework for effective and efficient point cloud analysis

Uses Software

• ImageNet
• PointNet
• PointCNN
• VoxelNet
• OctNet
• VoxNet
• Point2Sequence
• AlexNet

This page was built for publication: LRC-Net: learning discriminative features on point clouds by encoding local region contexts

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2180642)