Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation

11/14/2021
by   Jiajing Chen, et al.
2

With the proliferation of Lidar sensors and 3D vision cameras, 3D point cloud analysis has attracted significant attention in recent years. After the success of the pioneer work PointNet, deep learning-based methods have been increasingly applied to various tasks, including 3D point cloud segmentation and 3D object classification. In this paper, we propose a novel 3D point cloud learning network, referred to as Dynamic Point Feature Aggregation Network (DPFA-Net), by selectively performing the neighborhood feature aggregation with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3D point clouds. As the core module of the DPFA-Net, we propose a Feature Aggregation layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points, and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of the proposed semantic segmentation model, we present two novel approaches, namely Two-Stage BF-Net and BF-Regularization to exploit the background-foreground information. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score for semantic segmentation on the S3DIS dataset, and provides a consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3D object classification. It is also computationally more efficient compared to other methods.

READ FULL TEXT

page 1

page 3

page 5

page 9

page 12

research
01/30/2022

MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds

Semantic segmentation of 3D point cloud is an essential task for autonom...
research
11/02/2020

PBP-Net: Point Projection and Back-Projection Network for 3D Point Cloud Segmentation

Following considerable development in 3D scanning technologies, many stu...
research
07/28/2019

DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation

Traditional grid/neighbor-based static pooling has become a constraint f...
research
05/21/2022

Point is a Vector: A Feature Representation in Point Analysis

The irregularity and disorder of point clouds bring many challenges to p...
research
03/19/2023

GAM : Gradient Attention Module of Optimization for Point Clouds Analysis

In point cloud analysis tasks, the existing local feature aggregation de...
research
03/02/2022

A Unified Query-based Paradigm for Point Cloud Understanding

3D point cloud understanding is an important component in autonomous dri...
research
03/01/2022

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention

We present a simple but effective attention named the unary-pairwise att...

Please sign up or login with your details

Forgot password? Click here to reset