Research map / Point clouds / Shape and surface completion
SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization
Jheng-Wei Su, Kuei-Yu Tung, Chi-Han Peng, Peter Wonka, Hung-Kuo Chu
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 Box IoU loss (ablation) | SLIBO-Net box transformer · Structured3D test | Corner F1: 0.765 -> 0.854 | Improved |
| add Box IoU loss (ablation) | SLIBO-Net box transformer · Structured3D test | Angle F1: 0.749 -> 0.844 | Improved |
| add Box IoU loss (ablation) | SLIBO-Net box transformer · Structured3D test | Room F1: 0.972 -> 0.984 | Improved |
| add corner mask in corner loss (ablation) | SLIBO-Net box transformer · Structured3D test | Corner F1: 0.850 -> 0.854 | Improved |
| add corner mask in corner loss (ablation) | SLIBO-Net box transformer · Structured3D test | Angle F1: 0.84 -> 0.844 | Improved |
| add cell complex rounding in post-processing (ablation) | SLIBO-Net · Structured3D test | Corner F1: 0.745 -> 0.854 | Improved |
| add cell complex rounding in post-processing (ablation) | SLIBO-Net · Structured3D test | Room F1: 0.963 -> 0.984 | Improved |
| add gap filling in post-processing (ablation) | SLIBO-Net · Structured3D test | Corner F1: 0.849 -> 0.854 | Improved |
| cluster slicing boxes with ground-truth room centers instead of predicted (ablation) | SLIBO-Net · Structured3D test | Corner F1: 0.854 -> 0.861 | Improved |
| increase box transformer tokens from 50 to 100 (ablation) | SLIBO-Net · Structured3D test | Corner F1: 0.854 -> 0.827 | Hurt |
| increase box transformer tokens from 50 to 300 (ablation) | SLIBO-Net · Structured3D test | Corner F1: 0.854 -> 0.789 | Hurt |
| increase box transformer tokens from 50 to 300 (ablation) | SLIBO-Net · Structured3D test | training time (sec./epoch): 38.36 -> 59.97 | Hurt |
Later papers that compared with this method
2 later accepted papers report SLIBO-Net as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation (ECCV 2024 · better on 3 of 3 shared results)
- PolyRoom: Room-aware Transformer for Floorplan Reconstruction (ECCV 2024 · better on 2 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MonteFloor — MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans (ICCV 2021) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation (ECCV 2024 · 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 0.90)
- CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.88)
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.87)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · 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.
