Litcius/Paper detail

Hybrid Cross-Transformer-KPConv for Point Cloud Segmentation

Shuhuan Wen, Pengjiang Li, Hong Zhang

2023IEEE Signal Processing Letters11 citationsDOI

Abstract

Point cloud segmentation is one of the challenging areas due to its disorder and irregularity. Currently, a lot of work utilising Transformer instead of conventional convolution methods has been proposed, which can well cope with these difficulties and is suitable for point cloud segmentation tasks. However, most existing Transformer methods extract global or local features in isolation, failing to obtain rich contextual information. In this letter, a cross-scale Transformer network for feature extration is proposed. Multi-level contextual information is captured appllying FPS algorithm. Integrated with point cloud convolution method, achieving excellent segmentation performance. Extensive experiments on SemanticKITTI dataset demonstrate the superior performance of the proposed method on mIoU.

Topics & Concepts

SegmentationComputer sciencePoint cloudTransformerArtificial intelligenceImage segmentationCloud computingConvolution (computer science)Feature extractionPattern recognition (psychology)Computer visionData miningEngineeringArtificial neural networkOperating systemElectrical engineeringVoltageRemote Sensing and LiDAR Applications3D Shape Modeling and Analysis3D Surveying and Cultural Heritage
Hybrid Cross-Transformer-KPConv for Point Cloud Segmentation | Litcius