Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes

TL;DR

This document describes two LaTeX class files, cas-sc.cls and cas-dc.cls, along with their templates, designed to support Elsevier's updated manuscript submission workflow. It covers layout support for both single-column and two-column formats and ensures compatibility with Elsevier's electronic submission system and alternative venues. The documentation explains front matter management, including long front matter handling via the longmktitle option, and details macros for author roles, affiliations, ORCID IDs, footnotes, and corresponding-author notation. Together, these tools streamline manuscript preparation and ensure compliance with journal formatting requirements for efficient submission and processing.

Abstract

Thanks to the application of deep learning technology in point cloud processing of the remote sensing field, point cloud segmentation has become a research hotspot in recent years, which can be applied to real-world 3D, smart cities, and other fields. Although existing solutions have made unprecedented progress, they ignore the inherent characteristics of point clouds in remote sensing fields that are strictly arranged according to latitude, longitude, and altitude, which brings great convenience to the segmentation of point clouds in remote sensing fields. To consider this property cleverly, we propose novel convolution operators, termed Twin Deformable point Convolutions (TDConvs), which aim to achieve adaptive feature learning by learning deformable sampling points in the latitude-longitude plane and altitude direction, respectively. First, to model the characteristics of the latitude-longitude plane, we propose a Cylinder-wise Deformable point Convolution (CyDConv) operator, which generates a two-dimensional cylinder map by constructing a cylinder-like grid in the latitude-longitude direction. Furthermore, to better integrate the features of the latitude-longitude plane and the spatial geometric features, we perform a multi-scale fusion of the extracted latitude-longitude features and spatial geometric features, and realize it through the aggregation of adjacent point features of different scales. In addition, a Sphere-wise Deformable point Convolution (SpDConv) operator is introduced to adaptively offset the sampling points in three-dimensional space by constructing a sphere grid structure, aiming at modeling the characteristics in the altitude direction. Experiments on existing popular benchmarks conclude that our TDConvs achieve the best segmentation performance, surpassing the existing state-of-the-art methods.