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

• URL: http://arxiv.org/abs/2508.19003v1
• Date: Tue, 26 Aug 2025 13:03:05 GMT
• Title: RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation
• Abstract summary: Roof plane segmentation is one of the key procedures for reconstructing 3D building models at levels of detail (LoD) 2 and 3 from airborne light detection and ranging (LiDAR) point clouds.<n>Current approaches for roof plane segmentation rely on the manually designed or learned features followed by some specifically designed geometric clustering strategies.<n>We propose a novel edge-aware transformer-based network, named RoofSeg, for segmenting roof planes from LiDAR point clouds in a truly end-to-end manner.
• Score: 7.458061089808731
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Hierarchical Space Partition for Surface Reconstruction [2.261077353537038]
  We propose a plane assembling strategy that effectively recovers missing details while maintaining model compactness.<n>We classify all the planes extracted from the scene into three categories: highly visible, barely visible, and invisible.<n>The invisible planes, which are recovered by scene structure analysis, indicate the missing details.
  arXiv  Detail & Related papers  (2026-06-03T13:52:36Z)
• LitePT: Lighter Yet Stronger Point Transformer [50.6430530112838]
  We analyse the role of different computational blocks in 3D point cloud networks.<n>We propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers.<n>The resulting LitePT model has $3.6times$ fewer parameters, runs $2times$ faster, and uses $2times$ less memory than the state-of-the-art Point Transformer V3.
  arXiv  Detail & Related papers  (2025-12-15T18:59:57Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds [14.67024375365087]
  Transformers have been seldom employed in point cloud roof plane instance segmentation.<n>Existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints.<n>We establish two criteria that high-quality superpoints should satisfy and introduce a corresponding two-stage superpoint generation process.
  arXiv  Detail & Related papers  (2025-05-30T11:23:16Z)
• Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation [38.81275292687583]
  We propose Plane2Depth, which adaptively utilizes plane information to improve depth prediction within a hierarchical framework. In the proposed plane guided depth generator (PGDG), we design a set of plane queries as prototypes to softly model planes in the scene and predict per-pixel plane coefficients. In the proposed adaptive plane query aggregation (APGA) module, we introduce a novel feature interaction approach to improve the aggregation of multi-scale plane features.
  arXiv  Detail & Related papers  (2024-09-04T07:45:06Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings [26.845588648999417]
  We tackle the problem of estimating the planar surfaces in a 3D scene from posed images. We propose a method that predicts multi-view consistent plane embeddings that complement geometry when clustering points into planes. We show through extensive evaluation on the ScanNetV2 dataset that our new method outperforms existing approaches.
  arXiv  Detail & Related papers  (2024-06-13T09:49:31Z)
• Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
  We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization. Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information. Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
  arXiv  Detail & Related papers  (2024-05-23T14:39:52Z)
• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation [9.944505802346733]
  Roof plane segmentation from airborne LiDAR point clouds is an important technology for 3D building model reconstruction. One of the key issues of plane segmentation is how to design powerful features that can distinguish adjacent planar patches. We propose a boundary-aware point clustering approach in Euclidean and embedding spaces constructed by a multi-task deep network for roof plane segmentation.
  arXiv  Detail & Related papers  (2023-09-07T13:58:31Z)
• Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection [92.75961303269548]
  The ground plane prior is a very informative geometry clue in monocular 3D object detection (M3OD) We propose a Ground Plane Enhanced Network (GPENet) which resolves both issues at one go. Our GPENet can outperform other methods and achieve state-of-the-art performance, well demonstrating the effectiveness and the superiority of the proposed approach.
  arXiv  Detail & Related papers  (2022-11-03T02:21:35Z)
• PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization [17.90299648470637]
  A novel 3D point cloud learning model for deep LiDAR odometry, named PWCLO-Net, is proposed in this paper. In this model, the Pyramid, Warping, and Cost volume structure for the LiDAR odometry task is built to refine the estimated pose in a coarse-to-fine approach hierarchically. Our method outperforms all recent learning-based methods and outperforms the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset.
  arXiv  Detail & Related papers  (2020-12-02T05:23:41Z)
• Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection [63.942632088208505]
  We propose a post-processing algorithm to align the segmented plane masks with edges detected in the image. This allows us to increase the accuracy of state-of-the-art approaches, while limiting ourselves to cuboid-shaped objects.
  arXiv  Detail & Related papers  (2020-03-28T18:51:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.