Structured Semantic 3D Reconstruction (S23DR) Challenge 2025 -- Winning solution
This addresses the challenge of 3D reconstruction for architectural modeling, but it is incremental as it builds on existing methods like PointNet for a specific competition.
The paper tackled the problem of predicting a house's 3D roof wireframe from sparse point clouds and semantic segmentations, achieving a winning Hybrid Structure Score (HSS) of 0.43 on the private leaderboard.
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.