SIESEF-FusionNet: Spatial Inter-correlation Enhancement and Spatially-Embedded Feature Fusion Network for LiDAR Point Cloud Semantic Segmentation

TL;DR

This paper introduces SIESEF-FusionNet, a novel neural network that enhances spatial inter-correlation and embeds spatial features to improve LiDAR point cloud semantic segmentation, especially at class boundaries.

Contribution

It proposes new modules for spatial inter-correlation enhancement and spatially-embedded feature fusion, improving segmentation accuracy and boundary delineation in LiDAR point clouds.

Findings

Achieves 83.7% mIoU on Toronto3D dataset.

Attains 61.1% mIoU on semanticKITTI dataset.

Demonstrates superior performance over baseline methods.

Abstract

The ambiguity at the boundaries of different semantic classes in point cloud semantic segmentation often leads to incorrect decisions in intelligent perception systems, such as autonomous driving. Hence, accurate delineation of the boundaries is crucial for improving safety in autonomous driving. A novel spatial inter-correlation enhancement and spatially-embedded feature fusion network (SIESEF-FusionNet) is proposed in this paper, enhancing spatial inter-correlation by combining inverse distance weighting and angular compensation to extract more beneficial spatial information without causing redundancy. Meanwhile, a new spatial adaptive pooling module is also designed, embedding enhanced spatial information into semantic features for strengthening the context-awareness of semantic features. Experimental results demonstrate that 83.7% mIoU and 97.8% OA are achieved by SIESEF-FusionNet on the Toronto3D dataset, with performance superior to other baseline methods. A value of 61.1% mIoU is reached on the semanticKITTI dataset, where a marked improvement in segmentation performance is observed. In addition, the effectiveness and plug-and-play capability of the proposed modules are further verified through ablation studies.