# AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motion

arXiv: https://arxiv.org/abs/2301.12135 · HTML: https://mlsanity.com/paper/2301.12135/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 28 Jan 2023.

## Builds on (most cited first, 19 of 19)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation](https://mlsanity.com/paper/2109.00524/) (2021)
- [4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving](https://mlsanity.com/paper/2009.06364/) (2020)
- [Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras](https://mlsanity.com/paper/1708.07878/) (2017)
- [Robust Camera Location Estimation by Convex Programming](https://mlsanity.com/paper/1412.0165/) (2014)
- [Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization](https://mlsanity.com/paper/1804.05625/) (2018)
- [Baseline Desensitizing In Translation Averaging](https://mlsanity.com/paper/1901.00643/) (2019)
- [Graph-Based Parallel Large Scale Structure from Motion](https://mlsanity.com/paper/1912.10659/) (2019)
- [Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approach](https://mlsanity.com/paper/2101.09116/) (2021)
- [ShapeFit and ShapeKick for Robust, Scalable Structure from Motion](https://mlsanity.com/paper/1608.02165/) (2016)
- [Cross-Descriptor Visual Localization and Mapping](https://mlsanity.com/paper/2012.01377/) (2020)
- [Progressive Structure from Motion](https://mlsanity.com/paper/1803.07349/) (2018)
- [VIO-Aided Structure from Motion Under Challenging Environments](https://mlsanity.com/paper/2101.09657/) (2021)

## Built on by (most cited first, 5 of 5)

- [DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus](https://mlsanity.com/paper/2405.13943/) (2024)
- [DReg-NeRF: Deep Registration for Neural Radiance Fields](https://mlsanity.com/paper/2308.09386/) (2023)
- [SCALAR-NeRF: SCAlable LARge-scale Neural Radiance Fields for Scene Reconstruction](https://mlsanity.com/paper/2311.16657/) (2023)
- [3D Reconstruction via Incremental Structure From Motion](https://mlsanity.com/paper/2508.01019/) (2025)
- [MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenes](https://mlsanity.com/paper/2510.15467/) (2025)

## Abstract (arXiv)

Despite the impressive results achieved by many existing Structure from Motion (SfM) approaches, there is still a need to improve the robustness, accuracy, and efficiency on large-scale scenes with many outlier matches and sparse view graphs. In this paper, we propose AdaSfM: a coarse-to-fine adaptive SfM approach that is scalable to large-scale and challenging datasets. Our approach first does a coarse global SfM which improves the reliability of the view graph by leveraging measurements from low-cost sensors such as Inertial Measurement Units (IMUs) and wheel encoders. Subsequently, the view graph is divided into sub-scenes that are refined in parallel by a fine local incremental SfM regularised by the result from the coarse global SfM to improve the camera registration accuracy and alleviate scene drifts. Finally, our approach uses a threshold-adaptive strategy to align all local reconstructions to the coordinate frame of global SfM. Extensive experiments on large-scale benchmark datasets show that our approach achieves state-of-the-art accuracy and efficiency.