Research map / Point clouds / Point cloud classification
Bundle Pooling for Polygonal Architecture Segmentation Problem
Check 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 |
|---|---|---|---|
| use bundle pooling for polygon boundary estimation | Ours · Test set | IoU meanAP (0.50:0.95): 55.5 -> 56.4 | Helped |
| use bundle pooling for polygon boundary estimation | Ours · Test set | OKS meanAP (0.50:0.95): 41.8 -> 45.1 | Helped |
| use bundle pooling for polygon boundary estimation | Ours · Test set | IoU meanAP (0.50:0.95): 39.1 -> 56.4 | Helped |
| add mean, max, and global bundle feature pooling (ablation) | Ours polygon segmentation · Polygon segmentation, All | IoU: 0.73 -> 0.81 | Helped |
| add mean, max, and global bundle feature pooling (ablation) | Ours polygon segmentation · Polygon segmentation, All | average keypoint distance: 25.2 -> 15.8 | Helped |
| add mean pooling to max line pooling (ablation) | Ours polygon segmentation · Polygon segmentation, All | IoU: 0.76 -> 0.78 | Helped |
| add global bundle pooling to mean plus max line pooling (ablation) | Ours polygon segmentation · Polygon segmentation, All | IoU: 0.78 -> 0.81 | Helped |
| use max pooling alone instead of mean plus max pooling (ablation) | Ours VP assignment · All, Wall | accuracy: 97.1 -> 86.9 | Hurt |
| use max pooling alone instead of mean plus max pooling (ablation) | Ours VP assignment · All, Roof | accuracy: 96.2 -> 85.6 | Hurt |
| use learned bundle pooling instead of RANSAC line counting | VP assignment · All, Wall | accuracy: 89.9 / 83.7 -> 97.1 / 96.5 | Helped |
Closest papers by meaning
- VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation (CVPR 2023 · similarity 0.86)
- Joint Semantic-geometric Learning for Polygonal Building Segmentation (AAAI 2021 · similarity 0.86)
- TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building Segmentation (NeurIPS 2026 · similarity 0.85)
- CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.84)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.83)
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.82)
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.