Research map / Graph learning / Graph algorithms and clustering
Floor-SP: Inverse CAD for Floorplans by Sequential Room-Wise Shortest Path
Jiacheng Chen, Chen Liu, Jiaye Wu, Yasutaka Furukawa
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 |
|---|---|---|---|
| add DNN-based data term and consistency term (ablation) | Floor-SP · Floorplan test set (94 units) | Room precision: 75.1 -> 84.7 | Improved |
| add DNN-based data term (without consistency term) (ablation) | Floor-SP · Floorplan test set (94 units) | Room++ recall: 22.0 -> 48.5 | Improved |
| add consistency term (ablation) | Floor-SP · Floorplan test set (94 units) | Room++ precision: 49.4 -> 51.4 | Improved |
| add consistency term (ablation) | Floor-SP · Floorplan test set (94 units) | Corner recall: 82.3 -> 82.2 | No clear effect |
| add second round of coordinate descent (ablation) | Floor-SP · Floorplan test set (94 units) | Room precision: 83.9 -> 84.7 | Improved |
| add second round of coordinate descent (ablation) | Floor-SP · Floorplan test set (94 units) | Room++ recall: 48.7 -> 50.4 | Improved |
| add second round of coordinate descent (ablation) | Floor-SP · Floorplan test set (94 units) | Corner recall: 82.8 -> 82.2 | Mixed |
| replace FloorNet bottom-up corner detection plus IP with Floor-SP | FloorNet · Floorplan test set (94 units) | Room++ recall: 37.5 -> 50.4 | Improved |
| replace FloorNet with Floor-SP | FloorNet · Floorplan test set (94 units) | Corner precision: 95.0 -> 95.1 | No clear effect |
| replace FloorNet with Floor-SP | FloorNet · Floorplan test set (94 units) | Edge precision: 94.8 -> 90.2 | Hurt |
Closest papers by meaning
- FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans (ECCV 2018 · similarity 0.92)
- Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries (CVPR 2023 · similarity 0.90)
- PolyRoom: Room-aware Transformer for Floorplan Reconstruction (ECCV 2024 · similarity 0.89)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.86)
- CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.85)
- F3Loc: Fusion and Filtering for Floorplan Localization (CVPR 2024 · similarity 0.84)
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.
