RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation

TL;DR

RoofSeg is an innovative edge-aware transformer network that achieves end-to-end roof plane segmentation from LiDAR data, addressing edge accuracy and geometric constraints for improved 3D building modeling.

Contribution

The paper introduces RoofSeg, a novel transformer-based architecture with an edge-aware module and geometric loss, enabling truly end-to-end roof plane segmentation with enhanced edge and geometric accuracy.

Findings

Achieves accurate roof plane segmentation from LiDAR point clouds.

Outperforms existing methods in edge and geometric accuracy.

Provides a fully end-to-end deep learning solution.

Abstract

Roof plane segmentation is one of the key procedures for reconstructing three-dimensional (3D) building models at levels of detail (LoD) 2 and 3 from airborne light detection and ranging (LiDAR) point clouds. The majority of current approaches for roof plane segmentation rely on the manually designed or learned features followed by some specifically designed geometric clustering strategies. Because the learned features are more powerful than the manually designed features, the deep learning-based approaches usually perform better than the traditional approaches. However, the current deep learning-based approaches have three unsolved problems. The first is that most of them are not truly end-to-end, the plane segmentation results may be not optimal. The second is that the point feature discriminability near the edges is relatively low, leading to inaccurate planar edges. The third is that the planar geometric characteristics are not sufficiently considered to constrain the network training. To solve these issues, a novel edge-aware transformer-based network, named RoofSeg, is developed for segmenting roof planes from LiDAR point clouds in a truly end-to-end manner. In the RoofSeg, we leverage a transformer encoder-decoder-based framework to hierarchically predict the plane instance masks with the use of a set of learnable plane queries. To further improve the segmentation accuracy of edge regions, we also design an Edge-Aware Mask Module (EAMM) that sufficiently incorporates planar geometric prior of edges to enhance its discriminability for plane instance mask refinement. In addition, we propose an adaptive weighting strategy in the mask loss to reduce the influence of misclassified points, and also propose a new plane geometric loss to constrain the network training.