Research map / 3D vision / Face and shape
Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization
Thomas Holzmann, Michael Maurer, Friedrich Fraundorfer, Horst Bischof
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 |
|---|---|---|---|
| replace Labatut visibility energy with the proposed normalized visibility energy | visibility-only reconstruction · Residential Area | mean error (m): 0.035 -> 0.034 | Improved |
| replace Labatut visibility energy with the proposed normalized visibility energy | visibility-only reconstruction · Fountain-P11 | mean error (m): 0.037 -> 0.034 | Improved |
| replace Labatut visibility energy with the proposed normalized visibility energy | visibility-only reconstruction · Fountain-P11 | std of error (m): 0.146 -> 0.135 | Improved |
| replace Labatut visibility energy with the proposed normalized visibility energy | visibility-only reconstruction · Residential Area | std of error (m): 0.071 -> 0.069 | Improved |
| add semantic class-specific processing (Poisson surroundings, building-only planes) (ablation) | Proposed pipeline · House and Residential Area | visual quality of surroundings | Improved |
| use line-based plane detection instead of point-based RANSAC | plane detection · urban facades | plane completeness | Improved |
| Proposed vs Poisson | reconstruction · House | mean error (m): 0.165 -> 0.126 | Improved |
| Proposed vs Poisson | reconstruction · Residential Area | mean error (m): 0.101 -> 0.055 | Improved |
| Proposed vs Holzmann et al. | reconstruction · Residential Area | mean error (m): 0.415 -> 0.055 | Improved |
| apply lossless Quadric Edge Collapse to proposed mesh rather than Poisson mesh | mesh simplification · House | face reduction factor r: 0.154 vs 0.929 | Improved |
Closest papers by meaning
- Dense Semantic 3D Reconstruction (TPAMI 2016 · similarity 0.87)
- Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling (CVPR 2016 · similarity 0.86)
- Building Fusion: Semantic-aware Structural Building-scale 3D Reconstruction (TPAMI 2020 · similarity 0.86)
- Boundary-Aware 3D Building Reconstruction From a Single Overhead Image (CVPR 2020 · similarity 0.86)
- AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings (CVPR 2024 · similarity 0.85)
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (CVPR 2024 · similarity 0.83)
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.
