Research map / Detection and segmentation / CNN features
FloorPlanFormer: Multi-Task Transformer Network for Floor Plan Recognition with Outer-to-Inner Feature Refinement
Yun Liang, ZiHao Wu, Run Zheng, Shuai Xie, Bo Hong, Yishen Lin
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 GCAM (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.919 -> 0.931 | Improved |
| add MFRM with small kernels (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.919 -> 0.932 | Improved |
| use small-kernel MFRM instead of large-kernel MFRM (ablation) | FloorPlanFormer · FloorPlan8K | Total Accu.: 0.960 -> 0.964 | Improved |
| add GCAM and MFRM(S) together (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.919 -> 0.935 | Improved |
| add dice loss (ablation) | FloorPlanFormer · FloorPlan8K | Total Accu.: 0.951 -> 0.964 | Improved |
| add cross-entropy loss (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.917 -> 0.922 | Improved |
| add joint multi-task loss (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.922 -> 0.935 | Improved |
| set MFRM repeat k=2 and N=3 vs k=1 (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.930 -> 0.935 | Improved |
| increase MFRM repeats to k=3 (ablation) | FloorPlanFormer · FloorPlan8K | mIoU: 0.935 -> 0.934 | No clear effect |
| base multi-task network vs Mask2former | FloorPlanFormer · FloorPlan8K | Total Accu.: mIoU 0.915 -> 0.919; Total Accu. 0.957 -> 0.951 | Mixed |
| FloorPlanFormer full vs DeepFloorplan | FloorPlanFormer · FloorPlan8K | mIoU: 0.793 -> 0.935 | Improved |
Closest papers by meaning
- Deep Floor Plan Recognition Using a Multi-Task Network With Room-Boundary-Guided Attention (ICCV 2019 · similarity 0.89)
- End-to-End Graph-Constrained Vectorized Floorplan Generation with Panoptic Refinement (ECCV 2022 · similarity 0.87)
- VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation (CVPR 2023 · similarity 0.86)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · similarity 0.83)
- Geometric Exploitation for Indoor Panoramic Semantic Segmentation (NeurIPS 2024 · similarity 0.82)
- CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.82)
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.
