Large Scale SfM with the Distributed Camera Model

TL;DR

This paper introduces the distributed camera model for SfM, enabling efficient and robust large-scale 3D reconstruction by merging multiple cameras as a single entity, significantly improving performance over existing methods.

Contribution

The paper presents a novel distributed camera model and a large-scale SfM pipeline that improves efficiency and robustness, capable of reconstructing extensive scenes like Rome from thousands of images.

Findings

Solution up to 8 times more efficient than gDLS

Robust to rotation singularities

Reconstructed Rome from 15,000 images in 22 minutes

Abstract

We introduce the distributed camera model, a novel model for Structure-from-Motion (SfM). This model describes image observations in terms of light rays with ray origins and directions rather than pixels. As such, the proposed model is capable of describing a single camera or multiple cameras simultaneously as the collection of all light rays observed. We show how the distributed camera model is a generalization of the standard camera model and describe a general formulation and solution to the absolute camera pose problem that works for standard or distributed cameras. The proposed method computes a solution that is up to 8 times more efficient and robust to rotation singularities in comparison with gDLS. Finally, this method is used in an novel large-scale incremental SfM pipeline where distributed cameras are accurately and robustly merged together. This pipeline is a direct generalization of traditional incremental SfM; however, instead of incrementally adding one camera at a time to grow the reconstruction the reconstruction is grown by adding a distributed camera. Our pipeline produces highly accurate reconstructions efficiently by avoiding the need for many bundle adjustment iterations and is capable of computing a 3D model of Rome from over 15,000 images in just 22 minutes.