# Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity

## TL;DR

This paper introduces a scalable method for 3D surface reconstruction from multi-scale point clouds with extreme density variation, using octree partitioning, Delaunay tetrahedralization, and graph cut optimization to achieve high accuracy and efficiency.

## Contribution

It presents a novel scalable approach combining octree, Delaunay tetrahedralization, and graph cuts that handles extreme point density variations efficiently.

## Key findings

- Achieves high accuracy and completeness on public datasets.
- Handles datasets with over four orders of magnitude in point density.
- Processes 2 billion points with less than 9GB RAM.

## Abstract

In this paper we present a scalable approach for robustly computing a 3D surface mesh from multi-scale multi-view stereo point clouds that can handle extreme jumps of point density (in our experiments three orders of magnitude). The backbone of our approach is a combination of octree data partitioning, local Delaunay tetrahedralization and graph cut optimization. Graph cut optimization is used twice, once to extract surface hypotheses from local Delaunay tetrahedralizations and once to merge overlapping surface hypotheses even when the local tetrahedralizations do not share the same topology.This formulation allows us to obtain a constant memory consumption per sub-problem while at the same time retaining the density independent interpolation properties of the Delaunay-based optimization. On multiple public datasets, we demonstrate that our approach is highly competitive with the state-of-the-art in terms of accuracy, completeness and outlier resilience. Further, we demonstrate the multi-scale potential of our approach by processing a newly recorded dataset with 2 billion points and a point density variation of more than four orders of magnitude - requiring less than 9GB of RAM per process.