Efficient Initial Pose-graph Generation for Global SfM

TL;DR

This paper introduces novel methods to accelerate initial pose-graph generation in global SfM by leveraging graph paths, heuristic traversal, and inlier probability ordering, significantly reducing computation time.

Contribution

The paper presents three new techniques that eliminate the need for time-consuming tentative matching and verification steps in pose-graph creation.

Findings

Speeded up feature matching by 17 times

Reduced pose estimation time by 5 times

Validated on 402,130 image pairs from 1DSfM dataset

Abstract

We propose ways to speed up the initial pose-graph generation for global Structure-from-Motion algorithms. To avoid forming tentative point correspondences by FLANN and geometric verification by RANSAC, which are the most time-consuming steps of the pose-graph creation, we propose two new methods - built on the fact that image pairs usually are matched consecutively. Thus, candidate relative poses can be recovered from paths in the partly-built pose-graph. We propose a heuristic for the A* traversal, considering global similarity of images and the quality of the pose-graph edges. Given a relative pose from a path, descriptor-based feature matching is made "light-weight" by exploiting the known epipolar geometry. To speed up PROSAC-based sampling when RANSAC is applied, we propose a third method to order the correspondences by their inlier probabilities from previous estimations. The algorithms are tested on 402130 image pairs from the 1DSfM dataset and they speed up the feature matching 17 times and pose estimation 5 times.