Research map / Point clouds / Segmentation and detection
BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models
Shangfeng Huang, Ruisheng Wang, Xin Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train on simulated point clouds instead of real point clouds | PBWR · Building3D real test | ACO: 0.22 -> 0.36 | Hurt |
| train on simulated point clouds instead of real point clouds | PBWR · Building3D real test | Edge F1: 0.76 -> 0.65 | Hurt |
| train on simulated point clouds instead of real point clouds | EdgeDiff · Building3D real test | Corner F1: 0.84 -> 0.76 | Hurt |
| train on simulated point clouds instead of real point clouds | BWFormer · Building3D real test | Corner F1: 0.88 -> 0.82 | Hurt |
| train on simulated point clouds instead of real point clouds | BWFormer · Building3D real test | ACO: 0.20 -> 0.22 | No clear effect |
| train on simulated data vs real data across three methods | PBWR/EdgeDiff/BWFormer · Building3D real test | reconstruction metrics: e.g. Edge F1 0.79 -> 0.68 (EdgeDiff) | Mixed |
Closest papers by meaning
- Building3D: A Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds (ICCV 2023 · similarity 0.92)
- Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models (NeurIPS 2026 · similarity 0.89)
- "Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset" (ECCV 2022 · similarity 0.88)
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.86)
- ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points (CVPR 2025 · similarity 0.85)
- 3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
