# Hierarchical structure-and-motion recovery from uncalibrated images

arXiv: https://arxiv.org/abs/1506.00395 · HTML: https://mlsanity.com/paper/1506.00395/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2015.

## Built on by (most cited first, 7 of 7)

- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)
- [Parallel Structure from Motion for UAV Images via Weighted Connected Dominating Set](https://mlsanity.com/paper/2206.11499/) (2022)
- [Vision-Based Environmental Perception for Autonomous Driving](https://mlsanity.com/paper/2212.11453/) (2022)
- [On-the-Fly SfM: What you capture is What you get](https://mlsanity.com/paper/2309.11883/) (2023)
- [A Taxonomy of Structure from Motion Methods](https://mlsanity.com/paper/2505.15814/) (2025)
- [Optimal Triangulation Method is Not Really Optimal](https://mlsanity.com/paper/2107.04618/) (2021)
- [Pointless Global Bundle Adjustment With Relative Motions Hessians](https://mlsanity.com/paper/2304.05118/) (2023)

## Abstract (arXiv)

This paper addresses the structure-and-motion problem, that requires to find camera motion and 3D struc- ture from point matches. A new pipeline, dubbed Samantha, is presented, that departs from the prevailing sequential paradigm and embraces instead a hierarchical approach. This method has several advantages, like a provably lower computational complexity, which is necessary to achieve true scalability, and better error containment, leading to more stability and less drift. Moreover, a practical autocalibration procedure allows to process images without ancillary information. Experiments with real data assess the accuracy and the computational efficiency of the method.