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

## TL;DR

This paper introduces an automatic method for reconstructing detailed volumetric 3D building models from unstructured indoor point clouds using integer linear programming, enabling precise and consistent models without prior segmentation.

## Contribution

It presents a fully automatic approach that combines room segmentation, outlier removal, and an integer linear optimization to produce accurate volumetric building models from raw point cloud data.

## Key findings

- Successfully reconstructs complex building models from real-world data
- Enforces volumetric, interconnected wall structures for realistic models
- Uses exact integer linear programming for optimal solutions

## Abstract

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.