Key Concepts
- VO vs SLAM — VO is local (no loop closure), SLAM includes global map + loop closure
- Scale ambiguity — Fundamental limitation of monocular SLAM; absolute scale is classically unrecoverable from geometry alone (learned metric-depth priors such as Metric3D or MASt3R can supply approximate scale)
- Covisibility graph — Shared map point visibility between keyframes; core data structure in ORB-SLAM
- Visual Place Recognition (VPR) — Recognizing previously visited places for loop closure
- Self-supervised depth — Learning monocular depth without ground truth (Monodepth2, Godard 2019)
Feature-based SLAM
| System | Author/Year | Key Concepts |
|---|---|---|
| Visual Odometry | Nistér 2004 | Five-point essential matrix solver, RANSAC, Triangulation, VO (local-only, no loop closure) |
| MonoSLAM | Davison 2007 | First real-time monocular SLAM, EKF-based, single camera, sparse 3D map, probabilistic feature initialization |
| PTAM | Klein & Murray 2007 | FAST feature, Tracking, Frontend/Backend separation, Parallel threads, Keyframe, Mapping, Bundle adjustment, Manual initialization |
| Visual-SLAM why filter? | Strasdat 2012 | Bundle adjustment, Scale-aware BA, Motion-only BA |
| ORB-SLAM | Mur-Artal 2015 | ORB keypoint, Automatic initialization (Homography vs Fundamental selection), Tracking thread, Local (covisibility-based) BA + global BA on loop closure, Local mapping, Large-scale, Loop closure, Bag of Visual Words, Global optimization, Covisibility graph, Map point management (culling, merging) |
| Pop-up SLAM | Yang 2016 | Line/Plane features |
| PL-SLAM | Pumarola 2017 | Point/Line features |
| ORB-SLAM2 | Mur-Artal 2017 | → Stereo SLAM, → RGB-D SLAM |
| CubeSLAM | Yang 2019 | Monocular 3D cuboid detection + SLAM, 9-DoF object representation |
| OpenVSLAM | Sumikura 2019 | ORB-based SLAM framework, perspective/fisheye/equirectangular camera models, map save/load + localization mode |
| Stella-VSLAM | Community 2021 | OpenVSLAM successor, license reboot (→ also in Level 7) |
| UcoSLAM | Muñoz-Salinas 2019 | Fiducial markers |
| DeepFusion | Laidlow 2019 | Dense monocular reconstruction, semi-dense MVS + CNN depth/gradient predictions, probabilistic fusion with learned uncertainties |
| ORB-SLAM3 | Campos 2020 | Monocular + Stereo + VIO, Multi-map, IMU integration |
| DXSLAM | Li 2020 | Deep features for SLAM |
| PyCuVSLAM | NVIDIA 2025 | Python + CUDA GPU-accelerated VSLAM toolkit (cuVSLAM wrapper; stereo/multi-camera VIO) |
Direct SLAM
| System | Author/Year | Key Concepts |
|---|---|---|
| DTAM | Newcombe 2011 | Dense mapping, Keyframe mapping, GPGPU |
| LSD-SLAM | Engel 2014 | Photometric error minimization, High gradient pixels/edges, Large scale, Loop closure, Pose graph optimization |
| DSO | Engel 2016 | Photometric bundle adjustment, Sliding window BA, No loop closure/global optimization |
| LDSO | Gao 2018 | DSO + Loop closure (BoW-based), addresses DSO's main weakness |
| CNN-SLAM | Tateno 2017 | Depth from LSD-SLAM + deep depth, Semantic label |
| DVSO | Yang 2018 | Deep single image depth estimation, StackNet |
| D3VO | Yang 2020 | Deep single image depth estimation, Deep pose, Deep aleatoric uncertainty |
Semi-direct (Hybrid)
| System | Author/Year | Key Concepts |
|---|---|---|
| SVO | Forster 2014 | FAST feature detection, sparse direct image alignment, depth filters |
| SVO2 | Forster 2017 | Multi-camera/Fisheye, Probabilistic depth estimation, Direct method convergence, Sparse method, Bundle adjustment |
| Stereo DSO | Wang 2017 | → Stereo SLAM |
| VI-DSO | von Stumberg 2018 | → VIO/VINS |
SfM Tools
| System | Author/Year | Key Concepts |
|---|---|---|
| COLMAP | Schönberger 2016 | De-facto standard incremental SfM + MVS pipeline (C++/CUDA, pycolmap bindings) |
| GLOMAP | Pan 2024 | Global SfM revisited — COLMAP-compatible, much faster mapping |
| InstantSfM | Zhong 2025 | GPU-native sparse-aware SfM pipeline, large speedups over COLMAP |
Dynamic Environment SLAM
| System | Author/Year | Key Concepts |
|---|---|---|
| DynaSLAM | Bescós 2018 | Mask R-CNN dynamic-object removal + background inpainting, ORB-SLAM2-based |
| DS-SLAM | Yu 2018 | Semantic segmentation (SegNet) + motion consistency check |
| MaskFusion | Rünz 2018 | RGB-D recognition, tracking and reconstruction of multiple moving objects |
| MID-Fusion | Xu 2019 | Octree-based object-level multi-instance dynamic RGB-D SLAM |
| VDO-SLAM | Zhang 2020 | Dynamic object-aware SLAM, joint camera + object motion estimation |
| DynaSLAM II | Bescós 2021 | Tightly-coupled multi-object tracking and SLAM |
| MonST3R | Zhang 2024 | DUSt3R-family pointmap estimation in the presence of motion |