# Data-Efficient Decentralized Visual SLAM

arXiv: https://arxiv.org/abs/1710.05772 · HTML: https://mlsanity.com/paper/1710.05772/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2017.

## Built on by (most cited first, 23 of 23)

- [Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems](https://mlsanity.com/paper/2106.14386/) (2021)
- [Visual Place Recognition: A Tutorial](https://mlsanity.com/paper/2303.03281/) (2023)
- [Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems](https://mlsanity.com/paper/2301.06230/) (2023)
- [Probabilistic Visual Place Recognition for Hierarchical Localization](https://mlsanity.com/paper/2105.03091/) (2021)
- [Improving Visual Place Recognition Performance by Maximising Complementarity](https://mlsanity.com/paper/2102.08416/) (2021)
- [MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2112.01349/) (2021)
- [COVINS: Visual-Inertial SLAM for Centralized Collaboration](https://mlsanity.com/paper/2108.05756/) (2021)
- [Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems](https://mlsanity.com/paper/2109.12343/) (2021)
- [A Robot Web for Distributed Many-Device Localisation](https://mlsanity.com/paper/2202.03314/) (2022)
- [Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.04446/) (2022)
- [Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry](https://mlsanity.com/paper/2209.06588/) (2022)
- [That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation](https://mlsanity.com/paper/2403.04755/) (2024)
- [ORCHNet: A Robust Global Feature Aggregation approach for 3D LiDAR-based Place recognition in Orchards](https://mlsanity.com/paper/2303.00477/) (2023)
- [Collaborative Visual Inertial SLAM for Multiple Smart Phones](https://mlsanity.com/paper/2106.12186/) (2021)
- [Data Efficient Visual Place Recognition Using Extremely JPEG-Compressed Images](https://mlsanity.com/paper/2209.08343/) (2022)
- [COVINS-G: A Generic Back-end for Collaborative Visual-Inertial SLAM](https://mlsanity.com/paper/2301.07147/) (2023)
- [Data-Efficient Sequence-Based Visual Place Recognition with Highly Compressed JPEG Images](https://mlsanity.com/paper/2302.13314/) (2023)
- [Dynamic Visual SLAM using a General 3D Prior](https://mlsanity.com/paper/2512.06868/) (2025)
- [Learning-based Measurement Scheduling for Loosely-Coupled Cooperative Localization](https://mlsanity.com/paper/2112.02843/) (2021)
- [Cross-Camera View-Overlap Recognition](https://mlsanity.com/paper/2208.11661/) (2022)
- [KS-APR: Keyframe Selection for Robust Absolute Pose Regression](https://mlsanity.com/paper/2308.05459/) (2023)
- [Adaptive Consensus: A network pruning approach for decentralized optimization](https://mlsanity.com/paper/2309.02626/) (2023)
- [DVM-SLAM: Decentralized Visual Monocular Simultaneous Localization and Mapping for Multi-Agent Systems](https://mlsanity.com/paper/2503.04126/) (2025)

## Abstract (arXiv)

Decentralized visual simultaneous localization and mapping (SLAM) is a powerful tool for multi-robot applications in environments where absolute positioning systems are not available. Being visual, it relies on cameras, cheap, lightweight and versatile sensors, and being decentralized, it does not rely on communication to a central ground station. In this work, we integrate state-of-the-art decentralized SLAM components into a new, complete decentralized visual SLAM system. To allow for data association and co-optimization, existing decentralized visual SLAM systems regularly exchange the full map data between all robots, incurring large data transfers at a complexity that scales quadratically with the robot count. In contrast, our method performs efficient data association in two stages: in the first stage a compact full-image descriptor is deterministically sent to only one robot. In the second stage, which is only executed if the first stage succeeded, the data required for relative pose estimation is sent, again to only one robot. Thus, data association scales linearly with the robot count and uses highly compact place representations. For optimization, a state-of-the-art decentralized pose-graph optimization method is used. It exchanges a minimum amount of data which is linear with trajectory overlap. We characterize the resulting system and identify bottlenecks in its components. The system is evaluated on publicly available data and we provide open access to the code.