Research map / 3D vision / Face and shape
FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans
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 PointNet and image branches to the floorplan branch (full FloorNet) (ablation) | floorplan branch · Floorplan benchmark | relationship metric (%): 50.0 -> 56.8 | Improved |
| use FloorNet hybrid design instead of OctNet (ablation) | FloorNet · Floorplan benchmark | relationship metric (%): 13.5 -> 56.8 | Improved |
| add floorplan-to-PointNet unpooling (ablation) | FloorNet · Floorplan benchmark | relationship metric (%): 52.3 -> 56.8 | Improved |
| add PointNet-to-floorplan pooling (ablation) | FloorNet · Floorplan benchmark | relationship metric (%): 52.8 -> 56.8 | Improved |
| add image-to-floorplan pooling (ablation) | FloorNet · Floorplan benchmark | relationship metric (%): 56.8 -> 56.8 | No clear effect |
| add image-to-floorplan pooling (ablation) | FloorNet · Floorplan benchmark | icon precision (%): 50.5 -> 56.1 | Improved |
| add image-to-floorplan pooling (ablation) | FloorNet · Floorplan benchmark | room precision/recall (%): 83.1 -> 85.2 recall, 84.2 -> 83.6 precision | Mixed |
| add PointNet-to-floorplan pooling (ablation) | FloorNet · Floorplan benchmark | icon recall (%): 42.2 -> 57.8 | Improved |
| use PointNet branch alone instead of floorplan branch (ablation) | PointNet only · Floorplan benchmark | room precision (%): 76.3 -> 27.0 | Hurt |
| use image branch alone instead of floorplan branch (ablation) | Image branch only · Floorplan benchmark | relationship metric (%): 50.0 -> 0.0 | Hurt |
| use FloorNet instead of Tango Navigator App for wall geometry (ablation) | FloorNet · Wall line distance | average line distance (pixels): 2.72 -> 1.66 | Improved |
| train with all loss functions in one run instead of one by one (ablation) | FloorNet training · Floorplan benchmark | test performance | Hurt |
Closest papers by meaning
- Floor-SP: Inverse CAD for Floorplans by Sequential Room-Wise Shortest Path (ICCV 2019 · similarity 0.92)
- End-to-End Graph-Constrained Vectorized Floorplan Generation with Panoptic Refinement (ECCV 2022 · similarity 0.90)
- FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation (ECCV 2024 · similarity 0.89)
- Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries (CVPR 2023 · similarity 0.89)
- CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.87)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · similarity 0.86)
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.
