Research map / Point clouds / Point cloud classification
Modeling Urban Scenes From Pointclouds
William Nguatem, Helmut Mayer
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 |
|---|---|---|---|
| increase DP concentration parameter alpha from 5 to 15 (ablation) | MUSP nonparametric Bayesian clustering · Single-building scene (Fig. 10B) | number of clusters inferred: alpha = 5 vs alpha = 15; higher alpha finds more clusters | Mixed |
| add connected-component analysis with voxel-parallelism constraint after clustering | MUSP segmentation · Urban pointclouds with vegetation noise | robustness to over-segmentation | Improved |
| use two-level clustering with coreset initialization instead of random initialization on full data | MUSP Gibbs sampling · SfM/MVS pointclouds | convergence speed: coreset contains only 10% data | Improved |
| use clipped plane normals instead of per-point normals | MUSP segmentation · SfM/MVS urban scenes | normal stability and cost | Improved |
Closest papers by meaning
- Large Scale Urban Scene Modeling from MVS Meshes (ECCV 2018 · similarity 0.88)
- GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation (ECCV 2026 · similarity 0.88)
- Fast Building Instance Proxy Reconstruction for Large Urban Scenes (TPAMI 2024 · similarity 0.88)
- Building3D: A Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds (ICCV 2023 · similarity 0.88)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.85)
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (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.
