# Fast ORB-SLAM without Keypoint Descriptors

arXiv: https://arxiv.org/abs/2008.09870 · HTML: https://mlsanity.com/paper/2008.09870/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning](https://mlsanity.com/paper/2205.07439/) (2022)
- [LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives](https://mlsanity.com/paper/2404.09748/) (2024)
- [GRAND-SLAM: Local Optimization for Globally Consistent Large-Scale Multi-Agent Gaussian SLAM](https://mlsanity.com/paper/2506.18885/) (2025)
- [Sparse Optical Flow-Based Line Feature Tracking](https://mlsanity.com/paper/2204.03331/) (2022)
- [ResMatch: Residual Attention Learning for Local Feature Matching](https://mlsanity.com/paper/2307.05180/) (2023)
- [HIVE: HIerarchical Volume Encoding for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2408.01677/) (2024)
- [Impact of Underwater Image Enhancement on Feature Matching](https://mlsanity.com/paper/2507.21715/) (2025)
- [PLD-SLAM: A Real-Time Visual SLAM Using Points and Line Segments in Dynamic Scenes](https://mlsanity.com/paper/2207.10916/) (2022)
- [Edge-Assisted Multi-Robot Visual-Inertial SLAM with Efficient Communication](https://mlsanity.com/paper/2603.11085/) (2026)

## Abstract (arXiv)

Indirect methods for visual SLAM are gaining popularity due to their robustness to environmental variations. ORB-SLAM2 citeorbslam2 is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe. To overcome these problems, we present FastORB-SLAM which is lightweight and efficient as it tracks keypoints between adjacent frames without computing descriptors. To achieve this, a two-stage coarse-to-fine descriptor independent keypoint matching method is proposed based on sparse optical flow. In the first stage, we predict initial keypoint correspondences via a simple but effective motion model and then robustly establish the correspondences via pyramid-based sparse optical flow tracking. In the second stage, we leverage the constraints of the motion smoothness and epipolar geometry to refine the correspondences. In particular, our method computes descriptors only for keyframes. We test FastORB-SLAM on textitTUM and textitICL-NUIM RGB-D datasets and compare its accuracy and efficiency to nine existing RGB-D SLAM methods. Qualitative and quantitative results show that our method achieves state-of-the-art accuracy and is about twice as fast as the ORB-SLAM2.