# Accurate Visual-Inertial SLAM by Feature Re-identification

arXiv: https://arxiv.org/abs/2102.13438 · HTML: https://mlsanity.com/paper/2102.13438/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 26 Feb 2021.

## Builds on (most cited first, 29 of 29)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [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)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [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)
- [MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask](https://mlsanity.com/paper/2003.10955/) (2020)
- [The TUM VI Benchmark for Evaluating Visual-Inertial Odometry](https://mlsanity.com/paper/1804.06120/) (2018)
- [On-Manifold Preintegration for Real-Time Visual-Inertial Odometry](https://mlsanity.com/paper/1512.02363/) (2015)
- [The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos](https://mlsanity.com/paper/1812.05538/) (2018)
- [Deep Rigid Instance Scene Flow](https://mlsanity.com/paper/1904.08913/) (2019)
- [Large-scale, real-time visual-inertial localization revisited](https://mlsanity.com/paper/1907.00338/) (2019)
- [A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors](https://mlsanity.com/paper/1901.03642/) (2019)
- [Visual-Inertial Monocular SLAM with Map Reuse](https://mlsanity.com/paper/1610.05949/) (2016)
- [Lightweight Unsupervised Deep Loop Closure](https://mlsanity.com/paper/1805.07703/) (2018)
- [Visual-Inertial Navigation: A Concise Review](https://mlsanity.com/paper/1906.02650/) (2019)
- [Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight](https://mlsanity.com/paper/1712.00036/) (2017)
- [Online Temporal Calibration for Monocular Visual-Inertial Systems](https://mlsanity.com/paper/1808.00692/) (2018)
- [Direct Sparse Mapping](https://mlsanity.com/paper/1904.06577/) (2019)
- [GCNv2: Efficient Correspondence Prediction for Real-Time SLAM](https://mlsanity.com/paper/1902.11046/) (2019)
- [ORBSLAM-Atlas: a robust and accurate multi-map system](https://mlsanity.com/paper/1908.11585/) (2019)
- [Learnable Cost Volume Using the Cayley Representation](https://mlsanity.com/paper/2007.11431/) (2020)
- [Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM](https://mlsanity.com/paper/1803.01549/) (2018)
- [Robust Keyframe-based Dense SLAM with an RGB-D Camera](https://mlsanity.com/paper/1711.05166/) (2017)
- [An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM](https://mlsanity.com/paper/1903.08636/) (2019)
- [Learning Whole-Image Descriptors for Real-time Loop Detection andKidnap Recovery under Large Viewpoint Difference](https://mlsanity.com/paper/1904.06962/) (2019)

## Abstract (arXiv)

We propose a novel feature re-identification method for real-time visual-inertial SLAM. The front-end module of the state-of-the-art visual-inertial SLAM methods (e.g. visual feature extraction and matching schemes) relies on feature tracks across image frames, which are easily broken in challenging scenarios, resulting in insufficient visual measurement and accumulated error in pose estimation. In this paper, we propose an efficient drift-less SLAM method by re-identifying existing features from a spatial-temporal sensitive sub-global map. The re-identified features over a long time span serve as augmented visual measurements and are incorporated into the optimization module which can gradually decrease the accumulative error in the long run, and further build a drift-less global map in the system. Extensive experiments show that our feature re-identification method is both effective and efficient. Specifically, when combining the feature re-identification with the state-of-the-art SLAM method [11], our method achieves 67.3% and 87.5% absolute translation error reduction with only a small additional computational cost on two public SLAM benchmark DBs: EuRoC and TUM-VI respectively.