Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph

• URL: http://arxiv.org/abs/2604.02497v1
• Date: Thu, 02 Apr 2026 19:57:25 GMT
• Title: Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph
• Abstract summary: Reconstructing building wireframe from airborne LiDAR point clouds yields a compact, topology-centric representation that enables structural understanding beyond dense meshes.<n>Yet a key limitation persists: conventional methods have failed to achieve accurate wireframe reconstruction in regions afflicted by significant noise, sparsity, or internal corners.<n>This work utilizes the Delaunay graph as a geometric prior to define a geometrically adaptive search space.
• Score: 14.904870157395878
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reconstructing building wireframe from airborne LiDAR point clouds yields a compact, topology-centric representation that enables structural understanding beyond dense meshes. Yet a key limitation persists: conventional methods have failed to achieve accurate wireframe reconstruction in regions afflicted by significant noise, sparsity, or internal corners. This failure stems from the inability to establish an adaptive search space to effectively leverage the rich 3D geometry of large, sparse building point clouds. In this work, we address this challenge with Delaunay Canopy, which utilizes the Delaunay graph as a geometric prior to define a geometrically adaptive search space. Central to our approach is Delaunay Graph Scoring, which not only reconstructs the underlying geometric manifold but also yields region-wise curvature signatures to robustly guide the reconstruction. Built on this foundation, our corner and wire selection modules leverage the Delaunay-induced prior to focus on highly probable elements, thereby shaping the search space and enabling accurate prediction even in previously intractable regions. Extensive experiments on the Building3D Tallinn city and entry-level datasets demonstrate state-of-the-art wireframe reconstruction, delivering accurate predictions across diverse and complex building geometries.

Related papers

• SuperFlex: Deformable Superquadrics for Point Cloud Decomposition [49.51169535433531]
  Superquadrics have proven to provide a compact, geometrically meaningful representation for 3D objects.<n>Existing methods suffer from limited reconstruction accuracy, are restricted to rigid primitives, and lack robustness to partial point clouds.<n>We present SuperFlex, an enhanced framework that expands the expressive power and applicability of superquadric decompositions.
  arXiv  Detail & Related papers  (2026-07-01T14:51:14Z)
• VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching [39.72379398607968]
  We introduce VolFill, a generative framework that predicts the 3D structure of the complete scene.<n>Our method utilizes a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into a compact latent space.
  arXiv  Detail & Related papers  (2026-05-29T15:59:20Z)
• GGPT: Geometry Grounded Point Transformer [22.64445696362087]
  We introduce the Geometry-Grounded Point Transformer (GGPT), a framework that augments feed-forward reconstruction with reliable sparse geometric guidance.<n>Building on this foundation, we propose a geometry-guided 3D point transformer that refines dense point maps under explicit partial-geometry supervision.
  arXiv  Detail & Related papers  (2026-03-11T18:00:04Z)
• Affostruction: 3D Affordance Grounding with Generative Reconstruction [50.586896835836164]
  We propose Affostruction, a generative framework that reconstructs complete geometry from partial observations and grounds affordances on the full shape.<n>Affostruction achieves 19.1 aIoU on affordance grounding and 32.67 IoU for 3D reconstruction, enabling accurate affordance prediction on complete shapes.
  arXiv  Detail & Related papers  (2026-01-14T06:33:12Z)
• TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction [57.46712611558817]
  3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass.<n>Recent strategies align consecutive predictions by solving global transformation, yet our analysis reveals their fundamental limitations in assumption validity, local alignment scope, and robustness under noisy geometry.<n>We propose a higher-DOF and long-term alignment framework based on Thin Plate Spline, leveraging globally propagated control points to correct spatially varying inconsistencies.
  arXiv  Detail & Related papers  (2025-12-02T02:22:20Z)
• SF-Recon: Simplification-Free Lightweight Building Reconstruction via 3D Gaussian Splatting [15.642110732300191]
  This work presents SF-Recon, a method that directly reconstructs lightweight building surfaces from multi-view images without post-hoc mesh simplification.<n>Based on a proposed SF dataset, the experimental results demonstrate that our SF-Recon can directly reconstruct lightweight building models from multi-view imagery.
  arXiv  Detail & Related papers  (2025-11-17T11:50:52Z)
• G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior [53.762256749551284]
  We identify accurate geometry as the fundamental prerequisite for effectively exploiting generative models to enhance 3D scene reconstruction.<n>We incorporate this geometry guidance throughout the generative pipeline to improve visibility mask estimation, guide novel view selection, and enhance multi-view consistency when inpainting with video diffusion models.<n>Our method naturally supports single-view inputs and unposed videos, with strong generalizability in both indoor and outdoor scenarios.
  arXiv  Detail & Related papers  (2025-10-14T03:06:28Z)
• GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering [83.19049705653072]
  During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved. We propose a novel approach called GeoGaussian to mitigate this issue. Our proposed pipeline achieves state-of-the-art performance in novel view synthesis and geometric reconstruction.
  arXiv  Detail & Related papers  (2024-03-17T20:06:41Z)
• Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds [23.897507889025817]
  We present a learning-based approach to reconstruct buildings as 3D polygonal meshes from airborne LiDAR point clouds. Our model learns directly from the point cloud data, thereby reducing error propagation and increasing the fidelity of the reconstruction. We experimentally validate our method on a collection of airborne LiDAR data of Zurich, Berlin and Tallinn.
  arXiv  Detail & Related papers  (2024-03-04T15:46:50Z)
• Learning a Structured Latent Space for Unsupervised Point Cloud Completion [48.79411151132766]
  We propose a novel framework, which learns a unified and structured latent space that encoding both partial and complete point clouds. Our proposed method consistently outperforms state-of-the-art unsupervised methods on both synthetic ShapeNet and real-world KITTI, ScanNet, and Matterport3D datasets.
  arXiv  Detail & Related papers  (2022-03-29T13:58:44Z)
• PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
  Point cloud completion refers to completing 3D shapes from partial 3D point clouds. We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
  arXiv  Detail & Related papers  (2022-03-16T09:20:01Z)
• Curved Buildings Reconstruction from Airborne LiDAR Data by Matching and Deforming Geometric Primitives [13.777047260469677]
  We propose a new framework for curved building reconstruction via assembling and deforming geometric primitives. The presented framework is validated on several highly curved buildings collected by various LiDAR in different cities.
  arXiv  Detail & Related papers  (2020-03-22T16:05:10Z)

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.