# H-SLAM: Hybrid Direct-Indirect Visual SLAM

arXiv: https://arxiv.org/abs/2306.07363 · HTML: https://mlsanity.com/paper/2306.07363/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 12 Jun 2023.

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

- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (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)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [The TUM VI Benchmark for Evaluating Visual-Inertial Odometry](https://mlsanity.com/paper/1804.06120/) (2018)
- [LDSO: Direct Sparse Odometry with Loop Closure](https://mlsanity.com/paper/1808.01111/) (2018)
- [A Photometrically Calibrated Benchmark For Monocular Visual Odometry](https://mlsanity.com/paper/1607.02555/) (2016)
- [Direct Sparse Mapping](https://mlsanity.com/paper/1904.06577/) (2019)
- [Loosely-Coupled Semi-Direct Monocular SLAM](https://mlsanity.com/paper/1807.10073/) (2018)
- [FDMO: Feature Assisted Direct Monocular Odometry](https://mlsanity.com/paper/1804.05422/) (2018)
- [A Unified Formulation for Visual Odometry](https://mlsanity.com/paper/1903.04253/) (2019)

## Built on by (most cited first, 4 of 4)

- [MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting](https://mlsanity.com/paper/2409.13055/) (2024)
- [DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing](https://mlsanity.com/paper/2401.09160/) (2024)
- [Inline Photometrically Calibrated Hybrid Visual SLAM](https://mlsanity.com/paper/2409.16810/) (2024)
- [ADM-Fusion: Adaptive Deep Multi-Sensor Fusion for Robust Ego-Motion Estimation in Diverse Conditions](https://mlsanity.com/paper/2606.25111/) (2026)

## Abstract (arXiv)

The recent success of hybrid methods in monocular odometry has led to many attempts to generalize the performance gains to hybrid monocular SLAM. However, most attempts fall short in several respects, with the most prominent issue being the need for two different map representations (local and global maps), with each requiring different, computationally expensive, and often redundant processes to maintain. Moreover, these maps tend to drift with respect to each other, resulting in contradicting pose and scene estimates, and leading to catastrophic failure. In this paper, we propose a novel approach that makes use of descriptor sharing to generate a single inverse depth scene representation. This representation can be used locally, queried globally to perform loop closure, and has the ability to re-activate previously observed map points after redundant points are marginalized from the local map, eliminating the need for separate and redundant map maintenance processes. The maps generated by our method exhibit no drift between each other, and can be computed at a fraction of the computational cost and memory footprint required by other monocular SLAM systems. Despite the reduced resource requirements, the proposed approach maintains its robustness and accuracy, delivering performance comparable to state-of-the-art SLAM methods (e.g., LDSO, ORB-SLAM3) on the majority of sequences from well-known datasets like EuRoC, KITTI, and TUM VI. The source code is available at: https://github.com/AUBVRL/fslam_ros_docker.