Research map / Point clouds / Shape and surface completion
Edges Compete for Trust: Group Relative Edge Optimization for Building Reconstruction from Point Clouds
Yujun Liu, Ruisheng Wang, Xiang Ao, Haoyuan Shen, Kuihao Wang, Kun Zhou, Qingquan Li
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 GREO training strategy to EdgeDiff | EdgeDiff · Building3D Tallinn | WED: 0.255 -> 0.225 | Improved |
| add GREO training strategy to PBWR | PBWR · Building3D Tallinn | WED: 0.271 -> 0.250 | Improved |
| add GREO to EdgeDiff on Entry-level | EdgeDiff · Building3D Entry-level | WED: 0.115 -> 0.108 | Improved |
| add GREO to PBWR on Entry-level | PBWR · Building3D Entry-level | WED: 0.145 -> 0.130 | Improved |
| add reward-based cross-entropy loss L_CE (ablation) | EdgeDiff · Building3D Tallinn | WED: 0.255 -> 0.242 | Improved |
| add entropy regularization on top of L_CE (ablation) | EdgeDiff · Building3D Tallinn | WED: 0.242 -> 0.225 | Improved |
| add entropy regularization on top of L_CE (ablation) | PBWR · Building3D Tallinn | WED: 0.262 -> 0.250 | Improved |
| use z-score instead of no normalization for rewards (ablation) | EdgeDiff · Building3D Tallinn | WED: 0.249 -> 0.225 | Improved |
| use z-score instead of min-max normalization (ablation) | EdgeDiff · Building3D Tallinn | WED: 0.236 -> 0.225 | Improved |
| use absolute reward without normalization (ablation) | PBWR · Building3D Tallinn | WED: 0.271 -> 0.266 | No clear effect |
| combine Hausdorff, cosine and center terms in reward instead of Hausdorff only (ablation) | EdgeDiff · Building3D Tallinn | WED: 0.247 -> 0.225 | Improved |
| add center term to Hausdorff+cosine reward (ablation) | EdgeDiff · Building3D Tallinn | WED: 0.237 -> 0.225 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- BWFormer — BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer (CVPR 2025) · better on 5 of 6 shared results
- EdgeDiff — EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds (CVPR 2025) · better on 5 of 5 shared results
- PBWR — PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds (CVPR 2024) · 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
- EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds (CVPR 2025 · similarity 0.89)
- PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds (CVPR 2024 · similarity 0.86)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.85)
- BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer (CVPR 2025 · similarity 0.85)
- CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.84)
- ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points (CVPR 2025 · similarity 0.84)
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.
