# Automatic reconstruction of fully volumetric 3D building models from point clouds

arXiv: https://arxiv.org/abs/1907.00631 · HTML: https://mlsanity.com/paper/1907.00631/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [SpatialLM: Training Large Language Models for Structured Indoor Modeling](https://mlsanity.com/paper/2506.07491/) (2025)
- [S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representations](https://mlsanity.com/paper/2212.11770/) (2022)
- [Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories](https://mlsanity.com/paper/2103.00262/) (2021)
- [Learning High-level Semantic-Relational Concepts for SLAM](https://mlsanity.com/paper/2310.00401/) (2023)
- [Pose Normalization of Indoor Mapping Datasets Partially Compliant to the Manhattan World Assumption](https://mlsanity.com/paper/2107.07778/) (2021)
- [Open-source automatic pipeline for efficient conversion of large-scale point clouds to IFC format](https://mlsanity.com/paper/2503.11498/) (2025)

## Abstract (arXiv)

We present a novel method for reconstructing parametric, volumetric, multi-story building models from unstructured, unfiltered indoor point clouds by means of solving an integer linear optimization problem. Our approach overcomes limitations of previous methods in several ways: First, we drop assumptions about the input data such as the availability of separate scans as an initial room segmentation. Instead, a fully automatic room segmentation and outlier removal is performed on the unstructured point clouds. Second, restricting the solution space of our optimization approach to arrangements of volumetric wall entities representing the structure of a building enforces a consistent model of volumetric, interconnected walls fitted to the observed data instead of unconnected, paper-thin surfaces. Third, we formulate the optimization as an integer linear programming problem which allows for an exact solution instead of the approximations achieved with most previous techniques. Lastly, our optimization approach is designed to incorporate hard constraints which were difficult or even impossible to integrate before. We evaluate and demonstrate the capabilities of our proposed approach on a variety of complex real-world point clouds.