结构化语义 3D 重建(S23DR)挑战 2025 -- 获奖方案
计算机视觉与模式识别
2025-06-23 v1
摘要
本文介绍了 S23DR 挑战 2025 的获奖方案，该挑战涉及从稀疏点云预测房屋 3D 屋顶线框和语义分段。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.
引用
@article{arxiv.2506.16421,
title = {Structured Semantic 3D Reconstruction (S23DR) Challenge 2025 -- Winning solution},
author = {Jan Skvrna and Lukas Neumann},
journal= {arXiv preprint arXiv:2506.16421},
year = {2025}
}