DSGI-Net: Density-based Selective Grouping Point Cloud Learning Network for Indoor Scene

Wen, Xin; Duan, Yao; Xu, Kai; Zhu, Chenyang

DSGI-Net: Density-based Selective Grouping Point Cloud Learning Network for Indoor Scene

Files

cgf15218.pdf (12.92 MB)

Date

2024

Authors

Wen, Xin
Duan, Yao
Xu, Kai
Zhu, Chenyang

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

Indoor scene point clouds exhibit diverse distributions and varying levels of sparsity, characterized by more intricate geometry and occlusion compared to outdoor scenes or individual objects. Despite recent advancements in 3D point cloud analysis introducing various network architectures, there remains a lack of frameworks tailored to the unique attributes of indoor scenarios. To address this, we propose DSGI-Net, a novel indoor scene point cloud learning network that can be integrated into existing models. The key innovation of this work is selectively grouping more informative neighbor points in sparse regions and promoting semantic consistency of the local area where different instances are in proximity but belong to distinct categories. Furthermore, our method encodes both semantic and spatial relationships between points in local regions to reduce the loss of local geometric details. Extensive experiments on the ScanNetv2, SUN RGB-D, and S3DIS indoor scene benchmarks demonstrate that our method is straightforward yet effective.

CCS Concepts: Computing methodologies → Scene understanding

        @article{10.1111:cgf.15218
,
journal = {Computer Graphics Forum},
title = {{DSGI-Net: Density-based Selective Grouping Point Cloud Learning Network for Indoor Scene
}},
author = {Wen, Xin and 
Duan, Yao and 
Xu, Kai and 
Zhu, Chenyang
},
year = {2024
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.15218
}
}