# Good Feature Matching: Towards Accurate, Robust VO/VSLAM with Low Latency

arXiv: https://arxiv.org/abs/2001.00714 · HTML: https://mlsanity.com/paper/2001.00714/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jan 2020.

## Built on by (most cited first, 6 of 6)

- [Greedy-Based Feature Selection for Efficient LiDAR SLAM](https://mlsanity.com/paper/2103.13090/) (2021)
- [Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry](https://mlsanity.com/paper/2109.05975/) (2021)
- [A Model for Multi-View Residual Covariances based on Perspective Deformation](https://mlsanity.com/paper/2202.00765/) (2022)
- [Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks](https://mlsanity.com/paper/2107.11187/) (2021)
- [Efficient Map Sparsification Based on 2D and 3D Discretized Grids](https://mlsanity.com/paper/2303.10882/) (2023)
- [The Geometric Observability Index: Influence, Fisher Information, and Weak Observability in SE(3) Pose Estimation](https://mlsanity.com/paper/2602.05582/) (2026)

## Abstract (arXiv)

Analysis of state-of-the-art VO/VSLAM system exposes a gap in balancing performance (accuracy & robustness) and efficiency (latency). Feature-based systems exhibit good performance, yet have higher latency due to explicit data association; direct & semidirect systems have lower latency, but are inapplicable in some target scenarios or exhibit lower accuracy than feature-based ones. This paper aims to fill the performance-efficiency gap with an enhancement applied to feature-based VSLAM. We present good feature matching, an active map-to-frame feature matching method. Feature matching effort is tied to submatrix selection, which has combinatorial time complexity and requires choosing a scoring metric. Via simulation, the Max-logDet matrix revealing metric is shown to perform best. For real-time applicability, the combination of deterministic selection and randomized acceleration is studied. The proposed algorithm is integrated into monocular & stereo feature-based VSLAM systems. Extensive evaluations on multiple benchmarks and compute hardware quantify the latency reduction and the accuracy & robustness preservation.