A Unified View-Graph Selection Framework for Structure from Motion

TL;DR

This paper introduces a unified optimization framework for selecting view-graphs in structure from motion, improving accuracy and efficiency across diverse datasets by task-specific cost modeling and a network-flow based solution.

Contribution

It proposes a single, flexible view-graph selection framework that generalizes across different SfM objectives, unlike previous heuristic methods.

Findings

Enhanced reconstruction accuracy with disambiguation priors.

Efficient large-scale Internet dataset reconstruction.

Robust ghost-free reconstructions for ambiguous datasets.

Abstract

View-graph is an essential input to large-scale structure from motion (SfM) pipelines. Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph. Inconsistent or inaccurate edges can lead to inferior or wrong reconstruction. Most SfM methods remove `undesirable' images and pairs using several, fixed heuristic criteria, and propose tailor-made solutions to achieve specific reconstruction objectives such as efficiency, accuracy, or disambiguation. In contrast to these disparate solutions, we propose a single optimization framework that can be used to achieve these different reconstruction objectives with task-specific cost modeling. We also construct a very efficient network-flow based formulation for its approximate solution. The abstraction brought on by this selection mechanism separates the challenges specific to datasets and reconstruction objectives from the standard SfM pipeline and improves its generalization. This paper demonstrates the application of the proposed view-graph framework with standard SfM pipeline for two particular use-cases, (i) accurate and ghost-free reconstructions of highly ambiguous datasets using costs based on disambiguation priors, and (ii) accurate and efficient reconstruction of large-scale Internet datasets using costs based on commonly used priors.