PBWR: Parametric Building Wireframe Reconstruction from Aerial LiDAR Point Clouds

no code implementations • 18 Nov 2023 • Shangfeng Huang, Ruisheng Wang, Bo Guo, Hongxin Yang

In this paper, we present an end-to-end 3D building wireframe reconstruction method to regress edges directly from aerial LiDAR point clouds. Our method, named Parametric Building Wireframe Reconstruction (PBWR), takes aerial LiDAR point clouds and initial edge entities as input, and fully uses self-attention mechanism of transformers to regress edge parameters without any intermediate steps such as corner prediction.

Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds

no code implementations • 21 Jul 2023 • Ruisheng Wang, Shangfeng Huang, Hongxin Yang

Lack of building datasets has become a major obstacle for applying deep learning technology to specific domains such as urban modeling.

Autonomous Navigation Self-Supervised Learning

Building3D: A Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds

no code implementations • ICCV 2023 • Ruisheng Wang, Shangfeng Huang, Hongxin Yang

Lack of building datasets has become a major obstacle for applying deep learning technology to specific domains such as urban modeling.

Autonomous Navigation Self-Supervised Learning