GeoSegNet: point cloud semantic segmentation via geometric encoder-decoder modeling

doi:10.1007/s00371-023-02853-7

GeoSegNet: point cloud semantic segmentation via geometric encoder-decoder modeling

2023-05-29

3

PRE

AI

DOI：10.1007/s00371-023-02853-7

Original

Original request for help

Save

Abstract

En 中文

Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding. Although significant advances in recent years, most of the existing methods still suffer from either the object-level mis-classification or the boundary-level ambiguity. In this paper, we present a robust semantic segmentation network by deeply exploring the geometry of point clouds, dubbed GeoSegNet. Our GeoSegNet consists of a multi-geometry-based encoder and a boundary-guided decoder. In the encoder, we develop a new residual geometry module from multi-geometry perspectives to extract object-level features. In the decoder, we introduce a contrastive boundary learning module to enhance the geometric representation of boundary points. Benefiting from the geometric encoder-decoder modeling, GeoSegNet infers the segmentation of objects effectively while making the intersections (boundaries) of two or more objects clear. GeoSegNet achieves a significant performance with 64.9% mIoU on the challenging S3DIS dataset (Area 5) and 70.2% mIoU on S3DIS sixfold. Experiments show obvious improvements of GeoSegNet over its competitors in terms of the overall segmentation accuracy and object boundary clearness. Code is available at https://github.com/Chen-yuiyui/GeoSegNet.

Keywords:

GeoSegNet

Point cloud semantic segmentation

Residual geometry module

Contrastive boundary learning

GeoSegNet: point cloud semantic segmentation via geometric encoder-decoder modeling

Abstract

Journal

Organization