直接在3D点云上预测房屋屋顶线框，精度达0.43的领先方案。
Structured Semantic 3D Reconstruction (S23DR) Challenge 2025 -- Winning solution
- 先用视觉规律定位顶点候选，再分两阶段用点云网络优化与连线
- 在私有榜单上取得0.43的混合结构评分，为当前最佳结果
- 适合做3D建筑重建、智能设计辅助等场景的开发者参考
本文介绍S23DR Challenge 2025的获胜方案，目标是从稀疏点云和语义分割图中预测房屋的3D屋顶线框。方法直接在3D空间操作：首先利用Gestalt分组从COLMAP点云中识别顶点候选；随后采用两个类似PointNet的网络模型：第一个用于分析局部立方体区域，精炼并分类顶点；第二个处理连接顶点对的圆柱区域，预测边。该两阶段3D深度学习方法在私有榜单上获得0.43的混合结构评分（HSS），为最优成绩。
原文摘要 · Abstract (English)
This paper presents the winning solution for the S23DR Challenge 2025, which involves predicting a house's 3D roof wireframe from a sparse point cloud and semantic segmentations. Our method operates directly in 3D, first identifying vertex candidates from the COLMAP point cloud using Gestalt segmentations. We then employ two PointNet-like models: one to refine and classify these candidates by analyzing local cubic patches, and a second to predict edges by processing the cylindrical regions connecting vertex pairs. This two-stage, 3D deep learning approach achieved a winning Hybrid Structure Score (HSS) of 0.43 on the private leaderboard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。