Continuous Mapping Convolution for Large-Scale Point Clouds Semantic Segmentation

doi:10.1109/LGRS.2021.3107006

Continuous Mapping Convolution for Large-Scale Point Clouds Semantic Segmentation

2022-01-01

14

PRE

AI

DOI：10.1109/LGRS.2021.3107006

Original

Original request for help

Save

Abstract

En 中文

In this letter, we introduce MappingConvSeg, a continuous convolution network for semantic segmentation of large-scale point clouds. In particular, a conceptually simple, end-to-end learnable, and continuous convolution operator is proposed for learning spatial correlation of unstructured 3-D point clouds. For each local point set, the unstructured point features are first mapped onto a series of learned kernel points based on the spatial relationship, and the continuous convolution is then applied to capture specific local geometrical patterns. Taking the proposed mapping convolution operation as the building block, a hierarchical network is then built for large-scale point cloud semantic segmentation. Experimental results conducted on two public benchmarks, including Toronto-3D and Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset, demonstrate the superiority of the proposed method.

Keywords:

Kernel

Convolution

Three-dimensional displays

Semantics

Cloud computing

Feature extraction

Encoding

Continuous convolution

large-scale

point clouds

semantic segmentation

Continuous Mapping Convolution for Large-Scale Point Clouds Semantic Segmentation

Abstract

Journal

Organization