← Search

Shangfeng Huang

7 accepted papers

2026

BuildingGPT: Auto-Regressive Building Wireframe Reconstruction Model with Reinforcement Learning

CVPR 2026

In this paper, we propose BuildingGPT, a novel auto-regressive model for building wireframe reconstruction from point clouds with reinforcement learning.Unlike prior works based on detection or diffusion models, BuildingGPT reformulates the building wireframe reconstruction task into a sequence pred

Cited by 0SourcecodeScholar
2026

BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models

AAAI 2026technical

As digital twins become central to the transformation of modern cities, accurate and structured 3D building models emerge as a key enabler of high-fidelity, updatable urban representations. These models underpin diverse applications including energy modeling, urban planning, autonomous navigation, a

Cited by 0SourcePDFScholar
2025

BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer

CVPR 2025highlight

In this paper, we present BWFormer, a novel Transformer-based model for building wireframe reconstruction from airborne LiDAR point cloud. The problem is solved in a ground-up manner here by detecting the building corners in 2D, lifting and connecting them in 3D space afterwards with additional dat…

2025

Edge First: Edge-Guided Geometry for Superior 3D Roof Wireframe Reconstruction

ICASSP 2025accepted

Roof wireframe reconstruction has shown great success in 3D building reconstruction due to its lightweight nature and straightforward representation. However, previous methods consider all roof points, which result in edge redundancy and omissions. In this paper, we propose a novel and streamlined E…

Cited by 0SourceScholar
2025

EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds

CVPR 2025poster

Building reconstruction is a challenging problem at the intersection of computer vision, photogrammetry and computer graphics. 3D wireframe presents a compelling representation for building modeling through its compact structure. Existing wireframe reconstruction methods employing vertex detection a…

Cited by 0SourcePDFScholar
2024

PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds

CVPR 2024poster

In this paper we present an end-to-end 3D-building-wireframe reconstruction method to regress edges directly from aerial light-detection-and-ranging (LiDAR) point clouds. Our method named parametric-building-wireframe reconstruction (PBWR) takes aerial LiDAR point clouds and initial edge entities as…

Cited by 5SourcePDFScholar
2023

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

ICCV 2023poster

Urban modeling from LiDAR point clouds is an important topic in computer vision, computer graphics, photogrammetry and remote sensing. 3D city models have found a wide range of applications in smart cities, autonomous navigation, urban planning and mapping etc. However, existing datasets for 3D mode…

Cited by 32PDFScholar