# Structured Semantic 3D Reconstruction (S23DR) Challenge 2025 -- Winning solution

arXiv: https://arxiv.org/abs/2506.16421 · HTML: https://mlsanity.com/paper/2506.16421/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Builds on (most cited first, 2 of 2)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)

## Built on by (most cited first, 3 of 3)

- [SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video](https://mlsanity.com/paper/2606.01939/) (2026)
- [Edge Prediction for Roof Wireframe Reconstruction with Transformers](https://mlsanity.com/paper/2606.02406/) (2026)
- [S23DR 2026: End-to-End 3D Wireframe Prediction via DETR-Style Set Prediction with Contrastive Denoising](https://mlsanity.com/paper/2606.14811/) (2026)

## Abstract (arXiv)

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.