# Decentralization and Acceleration Enables Large-Scale Bundle Adjustment

arXiv: https://arxiv.org/abs/2305.07026 · HTML: https://mlsanity.com/paper/2305.07026/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 42 references that are in the map.
- First posted on arXiv 11 May 2023.

## Builds on (most cited first, 11 of 11)

- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [An Analysis of SVD for Deep Rotation Estimation](https://mlsanity.com/paper/2006.14616/) (2020)
- [Theseus: A Library for Differentiable Nonlinear Optimization](https://mlsanity.com/paper/2207.09442/) (2022)
- [Bundle Adjustment on a Graph Processor](https://mlsanity.com/paper/2003.03134/) (2020)
- [Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction](https://mlsanity.com/paper/2008.00446/) (2020)
- [Advances in Inference and Representation for Simultaneous Localization and Mapping](https://mlsanity.com/paper/2103.05041/) (2021)
- [MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2112.01349/) (2021)
- [Majorization Minimization Methods for Distributed Pose Graph Optimization](https://mlsanity.com/paper/2108.00083/) (2021)
- [Generalized Proximal Methods for Pose Graph Optimization](https://mlsanity.com/paper/2012.02709/) (2020)
- [Distributed Riemannian Optimization with Lazy Communication for Collaborative Geometric Estimation](https://mlsanity.com/paper/2203.00851/) (2022)
- [SymForce: Symbolic Computation and Code Generation for Robotics](https://mlsanity.com/paper/2204.07889/) (2022)

## Built on by (most cited first, 3 of 3)

- [Building Rome with Convex Optimization](https://mlsanity.com/paper/2502.04640/) (2025)
- [Bundle Adjustment in the Eager Mode](https://mlsanity.com/paper/2409.12190/) (2024)
- [InstantSfM: Towards GPU-Native SfM for the Deep Learning Era](https://mlsanity.com/paper/2510.13310/) (2025)

## Abstract (arXiv)

Scaling to arbitrarily large bundle adjustment problems requires data and compute to be distributed across multiple devices. Centralized methods in prior works are only able to solve small or medium size problems due to overhead in computation and communication. In this paper, we present a fully decentralized method that alleviates computation and communication bottlenecks to solve arbitrarily large bundle adjustment problems. We achieve this by reformulating the reprojection error and deriving a novel surrogate function that decouples optimization variables from different devices. This function makes it possible to use majorization minimization techniques and reduces bundle adjustment to independent optimization subproblems that can be solved in parallel. We further apply Nesterov's acceleration and adaptive restart to improve convergence while maintaining its theoretical guarantees. Despite limited peer-to-peer communication, our method has provable convergence to first-order critical points under mild conditions. On extensive benchmarks with public datasets, our method converges much faster than decentralized baselines with similar memory usage and communication load. Compared to centralized baselines using a single device, our method, while being decentralized, yields more accurate solutions with significant speedups of up to 953.7x over Ceres and 174.6x over DeepLM. Code: https://joeaortiz.github.io/daba.