Trilaminar Multiway Reconstruction Tree for Efficient Large Scale Structure from Motion

TL;DR

This paper introduces a unified framework for large-scale Structure from Motion that improves efficiency and accuracy by strategic image clustering and multi-start reconstruction, enabling faster processing and better scene completeness.

Contribution

The proposed method uniquely combines image clustering and multiple starting points to enhance reconstruction speed, accuracy, and robustness in large-scale SfM.

Findings

Significant speedup in reconstruction time

Higher accuracy compared to existing methods

Improved scene completeness and robustness

Abstract

Accuracy and efficiency are two key problems in large scale incremental Structure from Motion (SfM). In this paper, we propose a unified framework to divide the image set into clusters suitable for reconstruction as well as find multiple reliable and stable starting points. Image partitioning performs in two steps. First, some small image groups are selected at places with high image density, and then all the images are clustered according to their optimal reconstruction paths to these image groups. This promises that the scene is always reconstructed from dense places to sparse areas, which can reduce error accumulation when images have weak overlap. To enable faster speed, images outside the selected group in each cluster are further divided to achieve a greater degree of parallelism. Experiments show that our method achieves significant speedup, higher accuracy and better completeness.