# Efficient Initial Pose-graph Generation for Global SfM

arXiv: https://arxiv.org/abs/2011.11986 · HTML: https://mlsanity.com/paper/2011.11986/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 14 of 14)

- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [Finding Geometric Models by Clustering in the Consensus Space](https://mlsanity.com/paper/2103.13875/) (2021)
- [Space-Partitioning RANSAC](https://mlsanity.com/paper/2111.12385/) (2021)
- [Handbook on Leveraging Lines for Two-View Relative Pose Estimation](https://mlsanity.com/paper/2309.16040/) (2023)
- [AffineGlue: Joint Matching and Robust Estimation](https://mlsanity.com/paper/2307.15381/) (2023)
- [Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training](https://mlsanity.com/paper/2208.02709/) (2022)
- [Controllable RANSAC-based Anomaly Detection via Hypothesis Testing](https://mlsanity.com/paper/2410.15133/) (2024)
- [Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras](https://mlsanity.com/paper/2409.18673/) (2024)
- [Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations](https://mlsanity.com/paper/2504.15121/) (2025)
- [Global-Aware Edge Prioritization for Pose Graph Initialization](https://mlsanity.com/paper/2602.21963/) (2026)
- [A Multi-modal Garden Dataset and Hybrid 3D Dense Reconstruction Framework Based on Panoramic Stereo Images for a Trimming Robot](https://mlsanity.com/paper/2305.06278/) (2023)
- [MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion](https://mlsanity.com/paper/2507.03306/) (2025)
- [Pixel-Accurate Epipolar Guided Matching](https://mlsanity.com/paper/2603.18401/) (2026)
- [HiSfM: Disambiguating Structure-from-Motion via Scaffold-Anchored Hierarchical Reconstruction](https://mlsanity.com/paper/2609.04718/) (2026)

## Abstract (arXiv)

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.