Research map / 3D vision / Depth and stereo
Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans
Cheng Lin, Changjian Li, Wenping Wang
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 the closure term to the global placement energy (ablation) | Floorplan-Jigsaw global placement · Global layout placement (101 scenes) | ACC_global (%): 22.8 -> 85.1 | Improved |
| add the layout complexity term to the global placement energy (ablation) | Floorplan-Jigsaw global placement · Global layout placement (101 scenes) | ACC_global (%): 67.5 -> 85.1 | Improved |
| add the boundary similarity term to the global placement energy (ablation) | Floorplan-Jigsaw global placement · Global layout placement (101 scenes) | ACC_global (%): 80.2 -> 85.1 | Improved |
| use layout-based alignment instead of feature-descriptor registration (3DMatch) for small-overlap scans | partial scan alignment · SUNCG pose estimation | rotation error (deg): 43.41 -> 8.79 | Improved |
| use layout-based alignment instead of FPFH for small-overlap scans | partial scan alignment · SUNCG pose estimation | translation error (%): 29.12 -> 9.15 | Improved |
| use layout-based alignment instead of Manhattan-world OPVO for small-overlap scans | partial scan alignment · SUNCG pose estimation | translation error (%): 20.04 -> 9.15 | Improved |
| use the floorplan path method instead of RAPTER for structured modeling | layout reconstruction · Layout reconstruction (complete point clouds) | max error (%): 7.84 -> 2.57 | Improved |
| use the floorplan path method instead of MW Modeler for structured modeling | layout reconstruction · Layout reconstruction (complete point clouds) | average error (%): 1.22 -> 0.90 | Improved |
| increase the complexity penalty lambda (ablation) | local layout estimation · Partial layout estimation (401 fragments) | layout detail | Mixed |
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.
- 3DMatch — 3DMatch: Learning Local Geometric Descriptors From RGB-D Reconstructions (CVPR 2017) · better on 2 of 2 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
- HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.90)
- PolyLayout: Multi-room Manhattan Layout Estimation (ECCV 2026 · similarity 0.90)
- LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image (CVPR 2018 · similarity 0.89)
- FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation (ECCV 2024 · similarity 0.89)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · similarity 0.88)
- Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model (ICLR 2025 · similarity 0.87)
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.
