# LDSO: Direct Sparse Odometry with Loop Closure

arXiv: https://arxiv.org/abs/1808.01111 · HTML: https://mlsanity.com/paper/1808.01111/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2018.

## Built on by (most cited first, 30 of 51)

- [VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences](https://mlsanity.com/paper/2507.16443/) (2025)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction](https://mlsanity.com/paper/2604.08542/) (2026)
- [Deep Event Visual Odometry](https://mlsanity.com/paper/2312.09800/) (2023)
- [CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization](https://mlsanity.com/paper/2208.03660/) (2022)
- [Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2504.14516/) (2025)
- [MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry](https://mlsanity.com/paper/2409.09479/) (2024)
- [Advances in Inference and Representation for Simultaneous Localization and Mapping](https://mlsanity.com/paper/2103.05041/) (2021)
- [MBA-VO: Motion Blur Aware Visual Odometry](https://mlsanity.com/paper/2103.13684/) (2021)
- [From SLAM to Situational Awareness: Challenges and Survey](https://mlsanity.com/paper/2110.00273/) (2021)
- [DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2411.17660/) (2024)
- [GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats](https://mlsanity.com/paper/2503.08071/) (2025)
- [Asynchronous Multi-View SLAM](https://mlsanity.com/paper/2101.06562/) (2021)
- [Panoramic annular SLAM with loop closure and global optimization](https://mlsanity.com/paper/2102.13400/) (2021)
- [A Hybrid Sparse-Dense Monocular SLAM System for Autonomous Driving](https://mlsanity.com/paper/2108.07736/) (2021)
- [SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis](https://mlsanity.com/paper/2204.10211/) (2022)
- [PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM](https://mlsanity.com/paper/2410.12324/) (2024)
- [MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM](https://mlsanity.com/paper/2509.13536/) (2025)
- [LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction](https://mlsanity.com/paper/2512.13680/) (2025)
- [The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes](https://mlsanity.com/paper/2306.16917/) (2023)
- [MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing](https://mlsanity.com/paper/2412.20082/) (2024)
- [DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model](https://mlsanity.com/paper/2507.13145/) (2025)
- [Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry](https://mlsanity.com/paper/2102.01191/) (2021)
- [Comparison of modern open-source visual SLAM approaches](https://mlsanity.com/paper/2108.01654/) (2021)
- [Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications](https://mlsanity.com/paper/2203.01087/) (2022)
- [E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs](https://mlsanity.com/paper/2207.10008/) (2022)
- [H-SLAM: Hybrid Direct-Indirect Visual SLAM](https://mlsanity.com/paper/2306.07363/) (2023)
- [Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines](https://mlsanity.com/paper/2503.02955/) (2025)
- [SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes](https://mlsanity.com/paper/2511.18290/) (2025)

## Abstract (arXiv)

In this paper we present an extension of Direct Sparse Odometry (DSO) to a monocular visual SLAM system with loop closure detection and pose-graph optimization (LDSO). As a direct technique, DSO can utilize any image pixel with sufficient intensity gradient, which makes it robust even in featureless areas. LDSO retains this robustness, while at the same time ensuring repeatability of some of these points by favoring corner features in the tracking frontend. This repeatability allows to reliably detect loop closure candidates with a conventional feature-based bag-of-words (BoW) approach. Loop closure candidates are verified geometrically and Sim(3) relative pose constraints are estimated by jointly minimizing 2D and 3D geometric error terms. These constraints are fused with a co-visibility graph of relative poses extracted from DSO's sliding window optimization. Our evaluation on publicly available datasets demonstrates that the modified point selection strategy retains the tracking accuracy and robustness, and the integrated pose-graph optimization significantly reduces the accumulated rotation-, translation- and scale-drift, resulting in an overall performance comparable to state-of-the-art feature-based systems, even without global bundle adjustment.