Structured Semantic 3D Reconstruction (S23DR) Challenge 2025 -- Winning solution
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video
SAVMap extracts semantic structure points from panoramic video, tracks them across rectified views, and recovers 3D wireframe maps via Manhattan-constrained SfM, reporting 4.8 cm aggregate MAE over 5000 shelf elements...
-
Edge Prediction for Roof Wireframe Reconstruction with Transformers
Transformer model predicts 3D wireframe edges from semantically subsampled SfM points and frozen autoencoder features, achieving 0.6476 HSS on HoHo 22k dataset for second place in S23DR Challenge 2026.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.