Research map / 3D vision / Face and shape
Raster-To-Vector: Revisiting Floorplan Transformation
Chen Liu, Jiajun Wu, Pushmeet Kohli, 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 integer programming (full IP) after the CNN junction detection (ablation) | Raster-to-vector pipeline · Floorplan benchmark - wall junction | precision (%): 70.7 -> 94.7 | Improved |
| add integer programming (ablation) | Raster-to-vector pipeline · Floorplan benchmark - opening | precision (%): 67.9 -> 91.9 | Improved |
| add integer programming (ablation) | Raster-to-vector pipeline · Floorplan benchmark - icon | precision (%): 22.3 -> 84.0 | Improved |
| add integer programming (ablation) | Raster-to-vector pipeline · Floorplan benchmark - room | precision (%): 80.9 -> 84.5 | Improved |
| add integer programming (ablation) | Raster-to-vector pipeline · Floorplan benchmark - wall junction | recall (%): 95.1 -> 91.7 | Hurt |
| add integer programming (ablation) | Raster-to-vector pipeline · Floorplan benchmark - room | recall (%): 78.5 -> 88.4 | Improved |
| add mutual exclusion constraints to IP (ablation) | Raster-to-vector pipeline · Floorplan benchmark - opening | precision (%): 68.5 -> 91.9 | Improved |
| add mutual exclusion constraints to IP (ablation) | Raster-to-vector pipeline · Floorplan benchmark - icon | precision (%): 22.0 -> 84.0 | Improved |
| add mutual exclusion constraints to IP (ablation) | Raster-to-vector pipeline · Floorplan benchmark - wall junction | precision (%): 92.8 -> 94.7 | Improved |
| add mutual exclusion constraints to IP (ablation) | Raster-to-vector pipeline · Floorplan benchmark - room | recall (%): 87.5 -> 88.4 | Mixed |
| add loop constraints to IP (ablation) | Raster-to-vector pipeline · Floorplan benchmark - room | precision (%): 82.5 -> 84.5 | Improved |
| add loop constraints to IP (ablation) | Raster-to-vector pipeline · Floorplan benchmark - icon | recall (%): 75.0 -> 74.6 | No clear effect |
Closest papers by meaning
- End-to-End Graph-Constrained Vectorized Floorplan Generation with Panoptic Refinement (ECCV 2022 · similarity 0.90)
- HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising (CVPR 2023 · similarity 0.89)
- VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation (CVPR 2023 · similarity 0.89)
- FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans (ECCV 2018 · similarity 0.89)
- GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.88)
- F3Loc: Fusion and Filtering for Floorplan Localization (CVPR 2024 · 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.
