LRC-Net: Learning Discriminative Features on Point Clouds by EncodingLocal Region Contexts

03/18/2020
by   Xinhai Liu, et al.
0

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.

READ FULL TEXT

page 4

page 9

research
03/18/2020

LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts

Learning discriminative feature directly on point clouds is still challe...
research
08/29/2019

Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules

Learning discriminative shape representation directly on point clouds is...
research
11/06/2018

Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network

Exploring contextual information in the local region is important for sh...
research
03/01/2021

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

Accurately describing and detecting 2D and 3D keypoints is crucial to es...
research
04/15/2023

Region-Enhanced Feature Learning for Scene Semantic Segmentation

Semantic segmentation in complex scenes not only relies on local object ...
research
03/30/2023

Local region-learning modules for point cloud classification

Data organization via forming local regions is an integral part of deep ...
research
12/18/2018

Mo-Net: Flavor the Moments in Learning to Classify Shapes

A fundamental question in learning to classify 3D shapes is how to treat...

Please sign up or login with your details

Forgot password? Click here to reset