Research map / Detection and segmentation / CNN features
Joint Semantic-geometric Learning for Polygonal Building Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| jointly predict building segmentation, corner classes, and edge orientations, then generate and refine polygon vertices | Res-U-Net polygonal building segmentation · CrowdAI | F1: 71.7 -> 73.2 | Helped |
| jointly predict building segmentation, corner classes, and edge orientations, then generate and refine polygon vertices | Res-U-Net polygonal building segmentation · Vegas | F1-score: 88.5 -> 89.4 | Helped |
| use the proposed polygonal prediction method instead of ASIP | CrowdAI · CrowdAI | vertex F1₃px: 60.32 -> 66.96 | Helped |
| use the proposed polygonal prediction method instead of ASIP | CrowdAI · CrowdAI | vertex F1₅px: 78.00 -> 84.82 | Helped |
| add the vertex generation module to replace Douglas-Peucker simplification (ablation) | multi-task segmentation baseline · Vegas | vertex F1₃px: 50.94 -> 54.54 | Helped |
| add the vertex generation module to replace Douglas-Peucker simplification (ablation) | multi-task segmentation baseline · Vegas | vertex F1₅px: 75.47 -> 78.25 | Helped |
| add polygon refinement network to VGM-generated vertices (ablation) | VGM polygon prediction · Vegas | vertex F1₃px: 54.54 -> 65.37 | Helped |
| add polygon refinement network to VGM-generated vertices (ablation) | VGM polygon prediction · Vegas | vertex F1₅px: 78.25 -> 81.24 | Helped |
Closest papers by meaning
- Polygonal Building Extraction by Frame Field Learning (CVPR 2021 · similarity 0.90)
- PolyWorld: Polygonal Building Extraction With Graph Neural Networks in Satellite Images (CVPR 2022 · similarity 0.89)
- TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building Segmentation (NeurIPS 2026 · similarity 0.88)
- SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation (CVPR 2024 · similarity 0.84)
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (CVPR 2024 · similarity 0.84)
- Geometric Exploitation for Indoor Panoramic Semantic Segmentation (NeurIPS 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.