100多 項開源視覺 SLAM 方案夠你用了嗎？

前言：

最近在了解一些視覺SLAM算法，發現這篇文章總結的很不錯，是以給需要的朋友的也分享一下，感謝前輩的總結。

子產品介紹：

 1. 本文整理自我的 Github 倉庫（包括開源 SLAM 方案，近期論文）：

Visual_SLAM_Related_Researchgithub.com

 2.本文簡單将各種方案分為以下 7 類（固然有不少文章無法恰當分類，比如動态語義稠密建圖的 VISLAM +_+）：

• 一、Geometric SLAM
• 二、Semantic / Deep SLAM
• 三、Multi-Landmarks / Object SLAM
• 四、Sensor Fusion
• 五、Dynamic SLAM
• 六、Mapping
• 七、Optimization

• 

3. 由于此倉庫自 2019 年 3 月開始整理（20 年 3 月公開），是以以下的代碼除了經典的架構之外基本都集中在 19 年之後；此外個人比較關注 VO、物體級 SLAM 和多路标 SLAM，是以以下内容收集也不完整，無法涵蓋視覺 SLAM 的所有研究，也歡迎大家有好的方案可以在 issue 或評論中分享補充。

一、Geometric SLAM（23 項）

這一類是傳統的基于特征點、直接法或半直接法的幾何 SLAM。

1. PTAM

• 論文：Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C]//Mixed and Augmented Reality, 2007. ISMAR 2007. 6th IEEE and ACM International Symposium on. IEEE, 2007: 225-234.
• 代碼：github.com/Oxford-PTAM/
• 工程位址：robots.ox.ac.uk/~gk/PTA
• 作者其他研究：robots.ox.ac.uk/~gk/pub

2. S-PTAM（雙目 PTAM）

• 論文：Taihú Pire,Thomas Fischer, Gastón Castro, Pablo De Cristóforis, Javier Civera and Julio Jacobo Berlles. S-PTAM: Stereo Parallel Tracking and Mapping. Robotics and Autonomous Systems, 2017.
• 代碼：github.com/lrse/sptam
• 作者其他論文：Castro G, Nitsche M A, Pire T, et al. Efficient on-board Stereo SLAM through constrained-covisibility strategies[J]. Robotics and Autonomous Systems, 2019.

3. MonoSLAM

• 論文：Davison A J, Reid I D, Molton N D, et al. MonoSLAM: Real-time single camera SLAM[J]. IEEE transactions on pattern analysis and machine intelligence, 2007, 29(6): 1052-1067.
• 代碼：github.com/hanmekim/Sce

4. ORB-SLAM2

• 論文：Mur-Artal R, Tardós J D. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.
• 代碼：github.com/raulmur/ORB_
• 作者其他論文：
  • 單目半稠密建圖：Mur-Artal R, Tardós J D. Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM[C]//Robotics: Science and Systems. 2015, 2015.
  • VIORB：Mur-Artal R, Tardós J D. Visual-inertial monocular SLAM with map reuse[J]. IEEE Robotics and Automation Letters, 2017, 2(2): 796-803.
  • 多地圖：Elvira R, Tardós J D, Montiel J M M. ORBSLAM-Atlas: a robust and accurate multi-map system[J]. arXiv preprint arXiv:1908.11585, 2019.

以下 5, 6, 7, 8 幾項是 TUM 計算機視覺組全家桶，官方首頁

5. DSO

• 論文：Engel J, Koltun V, Cremers D. Direct sparse odometry[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 40(3): 611-625.
• 代碼：github.com/JakobEngel/d
• 雙目 DSO：Wang R, Schworer M, Cremers D. Stereo DSO: Large-scale direct sparse visual odometry with stereo cameras[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 3903-3911.
• VI-DSO：Von Stumberg L, Usenko V, Cremers D. Direct sparse visual-inertial odometry using dynamic marginalization[C]//2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018: 2510-2517.

6. LDSO

• 高翔在 DSO 上添加閉環的工作
• 論文：Gao X, Wang R, Demmel N, et al. LDSO: Direct sparse odometry with loop closure[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018: 2198-2204.
• 代碼：github.com/tum-vision/L

7. LSD-SLAM

• 論文：Engel J, Schöps T, Cremers D. LSD-SLAM: Large-scale direct monocular SLAM[C]//European conference on computer vision. Springer, Cham, 2014: 834-849.
• 代碼：github.com/tum-vision/l

8. DVO-SLAM

• 論文：Kerl C, Sturm J, Cremers D. Dense visual SLAM for RGB-D cameras[C]//2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2013: 2100-2106.
• 代碼 1：github.com/tum-vision/d
• 代碼 2：github.com/tum-vision/d
• 其他論文：
  • Kerl C, Sturm J, Cremers D. Robust odometry estimation for RGB-D cameras[C]//2013 IEEE international conference on robotics and automation. IEEE, 2013: 3748-3754.
  • Steinbrücker F, Sturm J, Cremers D. Real-time visual odometry from dense RGB-D images[C]//2011 IEEE international conference on computer vision workshops (ICCV Workshops). IEEE, 2011: 719-722.

9. SVO

• 蘇黎世大學機器人與感覺課題組
• 論文：Forster C, Pizzoli M, Scaramuzza D. SVO: Fast semi-direct monocular visual odometry[C]//2014 IEEE international conference on robotics and automation (ICRA). IEEE, 2014: 15-22.
• 代碼：github.com/uzh-rpg/rpg_
• Forster C, Zhang Z, Gassner M, et al. SVO: Semidirect visual odometry for monocular and multicamera systems[J]. IEEE Transactions on Robotics, 2016, 33(2): 249-265.

10. DSM

• 論文：Zubizarreta J, Aguinaga I, Montiel J M M. Direct sparse mapping[J]. arXiv preprint arXiv:1904.06577, 2019.
• 代碼：github.com/jzubizarreta ；Video

11. openvslam

• 論文：Sumikura S, Shibuya M, Sakurada K. OpenVSLAM: A Versatile Visual SLAM Framework[C]//Proceedings of the 27th ACM International Conference on Multimedia. 2019: 2292-2295.
• 代碼：github.com/xdspacelab/o ；文檔

12. se2lam（地面車輛位姿估計的視覺裡程計）

• 論文：Zheng F, Liu Y H. Visual-Odometric Localization and Mapping for Ground Vehicles Using SE (2)-XYZ Constraints[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 3556-3562.
• 代碼：github.com/izhengfan/se
• 作者的另外一項工作
  • 論文：Zheng F, Tang H, Liu Y H. Odometry-vision-based ground vehicle motion estimation with se (2)-constrained se (3) poses[J]. IEEE transactions on cybernetics, 2018, 49(7): 2652-2663.

13. GraphSfM（基于圖的并行大規模 SFM）

• 論文：Chen Y, Shen S, Chen Y, et al. Graph-Based Parallel Large Scale Structure from Motion[J]. arXiv preprint arXiv:1912.10659, 2019.
• 代碼：github.com/AIBluefisher

14. LCSD_SLAM（松耦合的半直接法單目 SLAM）

• 論文：Lee S H, Civera J. Loosely-Coupled semi-direct monocular SLAM[J]. IEEE Robotics and Automation Letters, 2018, 4(2): 399-406.
• 代碼：github.com/sunghoon031/ ；谷歌學術 ；示範視訊
• 作者另外一篇關于單目尺度的文章 代碼開源 ：Lee S H, de Croon G. Stability-based scale estimation for monocular SLAM[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 780-787.

15. RESLAM（基于邊的 SLAM）

• 論文：Schenk F, Fraundorfer F. RESLAM: A real-time robust edge-based SLAM system[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 154-160.
• 代碼：github.com/fabianschenk ； 項目首頁

16. scale_optimization（将單目 DSO 拓展到雙目）

• 論文：Mo J, Sattar J. Extending Monocular Visual Odometry to Stereo Camera System by Scale Optimization[C]. International Conference on Intelligent Robots and Systems (IROS), 2019.
• 代碼：github.com/jiawei-mo/sc

17. BAD-SLAM（直接法 RGB-D SLAM）

• 論文：Schops T, Sattler T, Pollefeys M. BAD SLAM: Bundle Adjusted Direct RGB-D SLAM[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 134-144.
• 代碼：github.com/ETH3D/badsla

18. GSLAM（內建 ORB-SLAM2，DSO，SVO 的通用架構）

• 論文：Zhao Y, Xu S, Bu S, et al. GSLAM: A general SLAM framework and benchmark[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 1110-1120.
• 代碼：github.com/zdzhaoyong/G

19. ARM-VO（運作于 ARM 處理器上的單目 VO）

• 論文：Nejad Z Z, Ahmadabadian A H. ARM-VO: an efficient monocular visual odometry for ground vehicles on ARM CPUs[J]. Machine Vision and Applications, 2019: 1-10.
• 代碼：github.com/zanazakaryai

20. cvo-rgbd（直接法 RGB-D VO）

• 論文：Ghaffari M, Clark W, Bloch A, et al. Continuous Direct Sparse Visual Odometry from RGB-D Images[J]. arXiv preprint arXiv:1904.02266, 2019.
• 代碼：github.com/MaaniGhaffar

21. Map2DFusion（單目 SLAM 無人機圖像拼接）

• 論文：Bu S, Zhao Y, Wan G, et al. Map2DFusion: Real-time incremental UAV image mosaicing based on monocular slam[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016: 4564-4571.
• 代碼：github.com/zdzhaoyong/M

22. CCM-SLAM（多機器人協同單目 SLAM）

• 論文：Schmuck P, Chli M. CCM‐SLAM: Robust and efficient centralized collaborative monocular simultaneous localization and mapping for robotic teams[J]. Journal of Field Robotics, 2019, 36(4): 763-781.
• 代碼：github.com/VIS4ROB-lab/ | Video

23. ORB-SLAM3

• 論文：Carlos Campos, Richard Elvira, et al.ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM[J]. arXiv preprint arXiv:2007.11898, 2020.
• 代碼：github.com/UZ-SLAMLab/O | Video

二、Semantic / Depp SLAM（16 項）

SLAM 與深度學習相結合的工作目前主要展現在兩個方面，一方面是将語義資訊參與到建圖、位姿估計等環節中，另一方面是端到端地完成 SLAM 的某一個步驟（比如 VO，閉環等）。個人對後者沒太關注，也同樣歡迎大家在 issue 中分享。

24. MsakFusion

• 論文：Runz M, Buffier M, Agapito L. Maskfusion: Real-time recognition, tracking and reconstruction of multiple moving objects[C]//2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). IEEE, 2018: 10-20.
• 代碼：github.com/martinruenz/

25. SemanticFusion

• 論文：McCormac J, Handa A, Davison A, et al. Semanticfusion: Dense 3d semantic mapping with convolutional neural networks[C]//2017 IEEE International Conference on Robotics and automation (ICRA). IEEE, 2017: 4628-4635.
• 代碼：github.com/seaun163/sem

26. semantic_3d_mapping

• 論文：Yang S, Huang Y, Scherer S. Semantic 3D occupancy mapping through efficient high order CRFs[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017: 590-597.
• 代碼：github.com/shichaoy/sem

27. Kimera（實時度量與語義定位建圖開源庫）

• 論文：Rosinol A, Abate M, Chang Y, et al. Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping[J]. arXiv preprint arXiv:1910.02490, 2019.
• 代碼：github.com/MIT-SPARK/Ki ；示範視訊

28. NeuroSLAM（腦啟發式 SLAM）

• 論文：Yu F, Shang J, Hu Y, et al. NeuroSLAM: a brain-inspired SLAM system for 3D environments[J]. Biological Cybernetics, 2019: 1-31.
• 代碼：github.com/cognav/Neuro
• 第四作者就是 Rat SLAM 的作者，文章也比較了十餘種腦啟發式的 SLAM

29. gradSLAM（自動分區的稠密 SLAM）

• 論文：Jatavallabhula K M, Iyer G, Paull L. gradSLAM: Dense SLAM meets Automatic Differentiation[J]. arXiv preprint arXiv:1910.10672, 2019.
• 代碼（預計 20 年 4 月放出）：github.com/montrealrobo ；項目首頁，示範視訊

30. ORB-SLAM2 + 目标檢測/分割的方案語義建圖

• github.com/floatlazer/s
• github.com/qixuxiang/or
• github.com/Ewenwan/ORB_

31. SIVO（語義輔助特征選擇）

• 論文：Ganti P, Waslander S. Network Uncertainty Informed Semantic Feature Selection for Visual SLAM[C]//2019 16th Conference on Computer and Robot Vision (CRV). IEEE, 2019: 121-128.
• 代碼：github.com/navganti/SIV

32. FILD（臨近圖增量式閉環檢測）

• 論文：Shan An, Guangfu Che, Fangru Zhou, Xianglong Liu, Xin Ma, Yu Chen.Fast and Incremental Loop Closure Detection using Proximity Graphs. pp. 378-385, The 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2019)
• 代碼：github.com/AnshanTJU/FI

33. object-detection-sptam（目标檢測與雙目 SLAM）

• 論文：Pire T, Corti J, Grinblat G. Online Object Detection and Localization on Stereo Visual SLAM System[J]. Journal of Intelligent & Robotic Systems, 2019: 1-10.
• 代碼：github.com/CIFASIS/obje

34. Map Slammer（單目深度估計 + SLAM）

• 論文：Torres-Camara J M, Escalona F, Gomez-Donoso F, et al. Map Slammer: Densifying Scattered KSLAM 3D Maps with Estimated Depth[C]//Iberian Robotics conference. Springer, Cham, 2019: 563-574.
• 代碼：github.com/jmtc7/mapSla

35. NOLBO（變分模型的機率 SLAM）

• 論文：Yu H, Lee B. Not Only Look But Observe: Variational Observation Model of Scene-Level 3D Multi-Object Understanding for Probabilistic SLAM[J]. arXiv preprint arXiv:1907.09760, 2019.
• 代碼：github.com/bogus2000/NO

36. GCNv2_SLAM （基于圖卷積神經網絡 SLAM）

• 論文：Tang J, Ericson L, Folkesson J, et al. GCNv2: Efficient correspondence prediction for real-time SLAM[J]. IEEE Robotics and Automation Letters, 2019, 4(4): 3505-3512.
• 代碼：github.com/jiexiong2016Video

37. semantic_suma（雷射語義建圖）

• 論文：Chen X, Milioto A, Palazzolo E, et al. SuMa++: Efficient LiDAR-based semantic SLAM[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019: 4530-4537.
• 代碼：github.com/PRBonn/seman ；Video

38. Neural-SLAM（主動神經 SLAM）

• 論文：Chaplot D S, Gandhi D, Gupta S, et al. Learning to explore using active neural slam[C]. ICLR 2020.
• 代碼：github.com/devendrachap

39. TartanVO：一種通用的基于學習的 VO

• 論文：Wang W, Hu Y, Scherer S. TartanVO: A Generalizable Learning-based VO[J]. arXiv preprint arXiv:2011.00359, 2020.
• 代碼：github.com/castacks/tar
• 資料集：IROS2020 TartanAir: A Dataset to Push the Limits of Visual SLAM，資料集位址

三、Multi-Landmarks / Object SLAM（15 項）

其實多路标的點、線、平面 SLAM 和物體級 SLAM 完全可以分類在 Geometric SLAM 和 Semantic SLAM 中，但個人對這一方向比較感興趣（也是我的研究所學生課題），是以将其獨立出來，開源方案相對較少，但很有意思。

40. PL-SVO（點線 SVO）

• 論文：Gomez-Ojeda R, Briales J, Gonzalez-Jimenez J. PL-SVO: Semi-direct Monocular Visual Odometry by combining points and line segments[C]//Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on. IEEE, 2016: 4211-4216.
• 代碼：github.com/rubengooj/pl

41. stvo-pl（雙目點線 VO）

• 論文：Gomez-Ojeda R, Gonzalez-Jimenez J. Robust stereo visual odometry through a probabilistic combination of points and line segments[C]//2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2016: 2521-2526.
• 代碼：github.com/rubengooj/st

42. PL-SLAM（點線 SLAM）

• 論文：Gomez-Ojeda R, Zuñiga-Noël D, Moreno F A, et al. PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments[J]. arXiv preprint arXiv:1705.09479, 2017.
• Gomez-Ojeda R, Moreno F A, Zuñiga-Noël D, et al. PL-SLAM: a stereo SLAM system through the combination of points and line segments[J]. IEEE Transactions on Robotics, 2019, 35(3): 734-746.

43. PL-VIO

• 論文：He Y, Zhao J, Guo Y, et al. PL-VIO: Tightly-coupled monocular visual–inertial odometry using point and line features[J]. Sensors, 2018, 18(4): 1159.
• 代碼：github.com/HeYijia/PL-V
• VINS + 線段：github.com/Jichao-Peng/

44. lld-slam（用于 SLAM 的可學習型線段描述符）

• 論文：Vakhitov A, Lempitsky V. Learnable line segment descriptor for visual SLAM[J]. IEEE Access, 2019, 7: 39923-39934.
• 代碼：github.com/alexandervak ；Video

點線結合的工作還有很多，國内的比如

+ 上交鄒丹平老師的 Zou D, Wu Y, Pei L, et al. StructVIO: visual-inertial odometry with structural regularity of man-made environments[J]. IEEE Transactions on Robotics, 2019, 35(4): 999-1013.

+ 浙大的 Zuo X, Xie X, Liu Y, et al. Robust visual SLAM with point and line features[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017: 1775-1782.

45. PlaneSLAM

• 論文：Wietrzykowski J. On the representation of planes for efficient graph-based slam with high-level features[J]. Journal of Automation Mobile Robotics and Intelligent Systems, 2016, 10.
• 代碼：github.com/LRMPUT/Plane
• 作者另外一項開源代碼，沒有找到對應的論文：github.com/LRMPUT/PUTSL

46. Eigen-Factors（特征因子平面對齊）

• 論文：Ferrer G. Eigen-Factors: Plane Estimation for Multi-Frame and Time-Continuous Point Cloud Alignment[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019: 1278-1284.
• 代碼：gitlab.com/gferrer/eige ；示範視訊

47. PlaneLoc

• 論文：Wietrzykowski J, Skrzypczyński P. PlaneLoc: Probabilistic global localization in 3-D using local planar features[J]. Robotics and Autonomous Systems, 2019, 113: 160-173.

48. Pop-up SLAM

• 論文：Yang S, Song Y, Kaess M, et al. Pop-up slam: Semantic monocular plane slam for low-texture environments[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016: 1222-1229.
• 代碼：github.com/shichaoy/pop

49. Object SLAM

• 論文：Mu B, Liu S Y, Paull L, et al. Slam with objects using a nonparametric pose graph[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016: 4602-4609.
• 代碼：github.com/BeipengMu/ob ；Video

50. voxblox-plusplus（物體級體素建圖）

• 論文：Grinvald M, Furrer F, Novkovic T, et al. Volumetric instance-aware semantic mapping and 3D object discovery[J]. IEEE Robotics and Automation Letters, 2019, 4(3): 3037-3044.
• 代碼：github.com/ethz-asl/vox

51. Cube SLAM

• 論文：Yang S, Scherer S. Cubeslam: Monocular 3-d object slam[J]. IEEE Transactions on Robotics, 2019, 35(4): 925-938.
• 代碼：github.com/shichaoy/cub
• 對，這就是帶我入坑的一項工作，2018 年 11 月份看到這篇論文（當時是預印版）之後開始學習物體級 SLAM，個人對 Cube SLAM 的一些注釋和總結：連結。
• 也有很多有意思的但沒開源的物體級 SLAM
  • Ok K, Liu K, Frey K, et al. Robust Object-based SLAM for High-speed Autonomous Navigation[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 669-675.
  • Li J, Meger D, Dudek G. Semantic Mapping for View-Invariant Relocalization[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 7108-7115.
  • Nicholson L, Milford M, Sünderhauf N. Quadricslam: Dual quadrics from object detections as landmarks in object-oriented slam[J]. IEEE Robotics and Automation Letters, 2018, 4(1): 1-8.

52. VPS-SLAM（平面語義 SLAM）

• 論文：Bavle H, De La Puente P, How J, et al. VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems[J]. IEEE Access, 2020.
• 代碼：bitbucket.org/hridaybav

53. Structure-SLAM-PointLine （室内環境單目點線 SLAM）

• 論文：Li Y, Brasch N, Wang Y, et al. Structure-SLAM: Low-Drift Monocular SLAM in Indoor Environments[J]. IEEE Robotics and Automation Letters, 2020, 5(4): 6583-6590.
• 代碼：github.com/yanyan-li/St

54. PL-VINS

• 論文：Fu Q, Wang J, Yu H, et al. PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line[J]. arXiv preprint arXiv:2009.07462, 2020.
• 代碼：github.com/cnqiangfu/PL

四、Sensor Fusion（19 項）

在傳感器融合方面隻關注了視覺 + 慣導，其他傳感器像 LiDAR，GPS 關注較少。

55. msckf_vio

• 論文：Sun K, Mohta K, Pfrommer B, et al. Robust stereo visual inertial odometry for fast autonomous flight[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 965-972.
• 代碼：github.com/KumarRobotic ；Video

56. rovio

• 論文：Bloesch M, Omari S, Hutter M, et al. Robust visual inertial odometry using a direct EKF-based approach[C]//2015 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, 2015: 298-304.
• 代碼：github.com/ethz-asl/rov ；Video

57. R-VIO

• 論文：Huai Z, Huang G. Robocentric visual-inertial odometry[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018: 6319-6326.
• 代碼：github.com/rpng/R-VIO ；Video

58. okvis

• 論文：Leutenegger S, Lynen S, Bosse M, et al. Keyframe-based visual–inertial odometry using nonlinear optimization[J]. The International Journal of Robotics Research, 2015, 34(3): 314-334.
• 代碼：github.com/ethz-asl/okv

59. VIORB

• 論文：Mur-Artal R, Tardós J D. Visual-inertial monocular SLAM with map reuse[J]. IEEE Robotics and Automation Letters, 2017, 2(2): 796-803.
• 代碼：github.com/jingpang/Lea （VIORB 本身是沒有開源的，這是王京大佬複現的一個版本）
• VI-ORB-SLAM2：github.com/YoujieXia/VI

60. VINS-mono

• 論文：Qin T, Li P, Shen S. Vins-mono: A robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018, 34(4): 1004-1020.
• 代碼：github.com/HKUST-Aerial
• 雙目版 VINS-Fusion：github.com/HKUST-Aerial
• 移動段 VINS-mobile：github.com/HKUST-Aerial

61. VINS-RGBD

• 論文：Shan Z, Li R, Schwertfeger S. RGBD-Inertial Trajectory Estimation and Mapping for Ground Robots[J]. Sensors, 2019, 19(10): 2251.
• 代碼：github.com/STAR-Center/ ；Video

62. Open-VINS

• 論文：Geneva P, Eckenhoff K, Lee W, et al. Openvins: A research platform for visual-inertial estimation[C]//IROS 2019 Workshop on Visual-Inertial Navigation: Challenges and Applications, Macau, China. IROS 2019.
• 代碼：github.com/rpng/open_vi

63. versavis（多功能的視慣傳感器系統）

• 論文：Tschopp F, Riner M, Fehr M, et al. VersaVIS—An Open Versatile Multi-Camera Visual-Inertial Sensor Suite[J]. Sensors, 2020, 20(5): 1439.
• 代碼：github.com/ethz-asl/ver

64. CPI（視慣融合的封閉式預積分）

• 論文：Eckenhoff K, Geneva P, Huang G. Closed-form preintegration methods for graph-based visual–inertial navigation[J]. The International Journal of Robotics Research, 2018.
• 代碼：github.com/rpng/cpi ；Video

65. TUM Basalt

• 論文：Usenko V, Demmel N, Schubert D, et al. Visual-inertial mapping with non-linear factor recovery[J]. IEEE Robotics and Automation Letters, 2019.
• 代碼：github.com/VladyslavUse ；Video；Project Page

66. Limo：雷射單目視覺裡程計

• 論文：Graeter J, Wilczynski A, Lauer M. Limo: Lidar-monocular visual odometry[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018: 7872-7879.
• 代碼：github.com/johannes-gra ；Video

67. LARVIO（多狀态限制卡爾曼濾波的單目 VIO）

• 論文：Qiu X, Zhang H, Fu W, et al. Monocular Visual-Inertial Odometry with an Unbiased Linear System Model and Robust Feature Tracking Front-End[J]. Sensors, 2019, 19(8): 1941.
• 代碼：github.com/PetWorm/LARV
• 北航邱笑晨博士的一項工作

68. vig-init（垂直邊緣加速視慣初始化）

• 論文：Li J, Bao H, Zhang G. Rapid and Robust Monocular Visual-Inertial Initialization with Gravity Estimation via Vertical Edges[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019: 6230-6236.
• 代碼：github.com/zju3dv/vig-i

69. vilib（VIO 前端庫）

• 論文：Nagy B, Foehn P, Scaramuzza D. Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO[J]. arXiv preprint arXiv:2003.13493, 2020.
• 代碼：github.com/uzh-rpg/vili

70. Kimera-VIO

• 論文：A. Rosinol, M. Abate, Y. Chang, L. Carlone, Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping. IEEE Intl. Conf. on Robotics and Automation (ICRA), 2020.
• 代碼：github.com/MIT-SPARK/Ki

71. maplab（視慣建圖架構）

• 論文：Schneider T, Dymczyk M, Fehr M, et al. maplab: An open framework for research in visual-inertial mapping and localization[J]. IEEE Robotics and Automation Letters, 2018, 3(3): 1418-1425.
• 代碼：github.com/ethz-asl/map
• 多會話建圖，地圖合并，視覺慣性批處理優化和閉環

72. lili-om：固态雷達慣性裡程計與建圖

• 論文：Li K, Li M, Hanebeck U D. Towards high-performance solid-state-lidar-inertial odometry and mapping[J]. arXiv preprint arXiv:2010.13150, 2020.
• 代碼：github.com/KIT-ISAS/lil

73. CamVox：Lidar輔助視覺 SLAM

• 論文：ZHU, Yuewen, et al. CamVox: A Low-cost and Accurate Lidar-assisted Visual SLAM System. arXiv preprint arXiv:2011.11357, 2020.
• 代碼：github.com/ISEE-Technol

五、Dynamic SLAM（8 項）

動态 SLAM 也是一個很值得研究的話題，這裡不太好分類，很多工作用到了語義資訊或者用來三維重建，收集的方案相對較少，歡迎補充 issue。

74. DynamicSemanticMapping（動态語義建圖）

• 論文：Kochanov D, Ošep A, Stückler J, et al. Scene flow propagation for semantic mapping and object discovery in dynamic street scenes[C]//Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on. IEEE, 2016: 1785-1792.
• 代碼：github.com/ganlumomo/Dy ；wiki

75. DS-SLAM（動态語義 SLAM）

• 論文：Yu C, Liu Z, Liu X J, et al. DS-SLAM: A semantic visual SLAM towards dynamic environments[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018: 1168-1174.
• 代碼：github.com/ivipsourceco

76. Co-Fusion（實時分割與跟蹤多物體）

• 論文：Rünz M, Agapito L. Co-fusion: Real-time segmentation, tracking and fusion of multiple objects[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2017: 4471-4478.
• 代碼：github.com/martinruenz/ ；Video

77. DynamicFusion

• 論文：Newcombe R A, Fox D, Seitz S M. Dynamicfusion: Reconstruction and tracking of non-rigid scenes in real-time[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 343-352.
• 代碼：github.com/mihaibujanca

78. ReFusion（動态場景利用殘差三維重建）

• 論文：Palazzolo E, Behley J, Lottes P, et al. ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals[J]. arXiv preprint arXiv:1905.02082, 2019.
• 代碼：github.com/PRBonn/refus ；Video

79. DynSLAM（室外大規模稠密重建）

• 論文：Bârsan I A, Liu P, Pollefeys M, et al. Robust dense mapping for large-scale dynamic environments[C]//2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018: 7510-7517.
• 代碼：github.com/AndreiBarsan
• 作者博士學位論文：Barsan I A. Simultaneous localization and mapping in dynamic scenes[D]. ETH Zurich, Department of Computer Science, 2017.

80. VDO-SLAM（動态物體感覺的 SLAM）

• 論文：Zhang J, Henein M, Mahony R, et al. VDO-SLAM: A Visual Dynamic Object-aware SLAM System[J]. arXiv preprint arXiv:2005.11052, 2020.（IJRR Under Review）
  • 相關論文
    • IROS 2020 Robust Ego and Object 6-DoF Motion Estimation and Tracking
    • ICRA 2020 Dynamic SLAM: The Need For Speed
• 代碼：github.com/halajun/VDO_ | video

六、Mapping（21 項）

針對建圖的工作一方面是利用幾何資訊進行稠密重建，另一方面很多工作利用語義資訊達到了很好的語義重建效果，三維重建、SFM 本身就是個很大的話題，開源代碼也很多，以下方案收集地可能也不太全。

81. InfiniTAM（跨平台 CPU 實時重建）

• 論文：Prisacariu V A, Kähler O, Golodetz S, et al. Infinitam v3: A framework for large-scale 3d reconstruction with loop closure[J]. arXiv preprint arXiv:1708.00783, 2017.
• 代碼：github.com/victorprad/I ；project page

82. BundleFusion

• 論文：Dai A, Nießner M, Zollhöfer M, et al. Bundlefusion: Real-time globally consistent 3d reconstruction using on-the-fly surface reintegration[J]. ACM Transactions on Graphics (TOG), 2017, 36(4): 76a.
• 代碼：github.com/niessner/Bun ；工程位址

83. KinectFusion

• 論文：Newcombe R A, Izadi S, Hilliges O, et al. KinectFusion: Real-time dense surface mapping and tracking[C]//2011 10th IEEE International Symposium on Mixed and Augmented Reality. IEEE, 2011: 127-136.
• 代碼：github.com/chrdiller/Ki

84. ElasticFusion

• 論文：Whelan T, Salas-Moreno R F, Glocker B, et al. ElasticFusion: Real-time dense SLAM and light source estimation[J]. The International Journal of Robotics Research, 2016, 35(14): 1697-1716.
• 代碼：github.com/mp3guy/Elast

85. Kintinuous

• ElasticFusion 同一個團隊的工作，帝國理工 Stefan Leutenegger 谷歌學術
• 論文：Whelan T, Kaess M, Johannsson H, et al. Real-time large-scale dense RGB-D SLAM with volumetric fusion[J]. The International Journal of Robotics Research, 2015, 34(4-5): 598-626.
• 代碼：github.com/mp3guy/Kinti

86. ElasticReconstruction

• 論文：Choi S, Zhou Q Y, Koltun V. Robust reconstruction of indoor scenes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 5556-5565.
• 代碼：github.com/qianyizh/Ela ；作者首頁

87. FlashFusion

• 論文：Han L, Fang L. FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU Computing[C]. RSS, 2018.
• 代碼（一直沒放出來）：github.com/lhanaf/Flash ；Project Page

88. RTAB-Map（雷射視覺稠密重建）

• 論文：Labbé M, Michaud F. RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation[J]. Journal of Field Robotics, 2019, 36(2): 416-446.
• 代碼：github.com/introlab/rta ；Video ；project page

89. RobustPCLReconstruction（戶外稠密重建）

• 論文：Lan Z, Yew Z J, Lee G H. Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 9690-9698.
• 代碼：github.com/ziquan111/Ro ；Video

90. plane-opt-rgbd（室内平面重建）

• 論文：Wang C, Guo X. Efficient Plane-Based Optimization of Geometry and Texture for Indoor RGB-D Reconstruction[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2019: 49-53.
• 代碼：github.com/chaowang15/p

91. DenseSurfelMapping（稠密表面重建）

• 論文：Wang K, Gao F, Shen S. Real-time scalable dense surfel mapping[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 6919-6925.

92. surfelmeshing（網格重建）

• 論文：Schöps T, Sattler T, Pollefeys M. Surfelmeshing: Online surfel-based mesh reconstruction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.
• 代碼：github.com/puzzlepaint/

93. DPPTAM（單目稠密重建）

• 論文：Concha Belenguer A, Civera Sancho J. DPPTAM: Dense piecewise planar tracking and mapping from a monocular sequence[C]//Proc. IEEE/RSJ Int. Conf. Intell. Rob. Syst. 2015 (ART-2015-92153).
• 代碼：github.com/alejocb/dppt
• 相關研究：基于超像素的單目 SLAM：Using Superpixels in Monocular SLAM ICRA 2014 ；谷歌學術

94. VI-MEAN（單目視慣稠密重建）

• 論文：Yang Z, Gao F, Shen S. Real-time monocular dense mapping on aerial robots using visual-inertial fusion[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2017: 4552-4559.
• 代碼：github.com/dvorak0/VI-M ；Video

95. REMODE（單目機率稠密重建）

• 論文：Pizzoli M, Forster C, Scaramuzza D. REMODE: Probabilistic, monocular dense reconstruction in real time[C]//2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2014: 2609-2616.
• 原始開源代碼：github.com/uzh-rpg/rpg_
• 與 ORB-SLAM2 結合版本：github.com/ayushgaud/ORgithub.com/ayushgaud/OR

96. DeepFactors（實時的機率單目稠密 SLAM）

• 帝國理工學院戴森機器人實驗室
• 論文：Czarnowski J, Laidlow T, Clark R, et al. DeepFactors: Real-Time Probabilistic Dense Monocular SLAM[J]. arXiv preprint arXiv:2001.05049, 2020.
• 代碼：github.com/jczarnowski/ （還未放出）
• 其他論文：Bloesch M, Czarnowski J, Clark R, et al. CodeSLAM—learning a compact, optimisable representation for dense visual SLAM[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 2560-2568.

97. probabilistic_mapping（單目機率稠密重建）

• 港科沈邵劼老師團隊
• 論文：Ling Y, Wang K, Shen S. Probabilistic dense reconstruction from a moving camera[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018: 6364-6371.
• 代碼：github.com/ygling2008/p
• 另外一篇稠密重建文章的代碼一直沒放出來 Github ：Ling Y, Shen S. Real‐time dense mapping for online processing and navigation[J]. Journal of Field Robotics, 2019, 36(5): 1004-1036.

98. ORB-SLAM2 單目半稠密建圖

• 論文：Mur-Artal R, Tardós J D. Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM[C]//Robotics: Science and Systems. 2015, 2015.
• 代碼（本身沒有開源，賀博複現的一個版本）：github.com/HeYijia/ORB_
• 加上線段之後的半稠密建圖
  • 論文：He S, Qin X, Zhang Z, et al. Incremental 3d line segment extraction from semi-dense slam[C]//2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 2018: 1658-1663.
  • 代碼：github.com/shidahe/semi
  • 作者在此基礎上用于指導遠端抓取操作的一項工作：github.com/atlas-jj/ORB

99. Voxgraph（SDF 體素建圖）

• 論文：Reijgwart V, Millane A, Oleynikova H, et al. Voxgraph: Globally Consistent, Volumetric Mapping Using Signed Distance Function Submaps[J]. IEEE Robotics and Automation Letters, 2019, 5(1): 227-234.

100. SegMap（三維分割建圖）

• 論文：Dubé R, Cramariuc A, Dugas D, et al. SegMap: 3d segment mapping using data-driven descriptors[J]. arXiv preprint arXiv:1804.09557, 2018.
• 代碼：github.com/ethz-asl/seg

101. OpenREALM：無人機實時建圖架構

• 論文：Kern A, Bobbe M, Khedar Y, et al. OpenREALM: Real-time Mapping for Unmanned Aerial Vehicles[J]. arXiv preprint arXiv:2009.10492, 2020.
• 代碼：github.com/laxnpander/O

七、Optimization（6 項）

個人感覺優化可能是 SLAM 中最難的一部分了吧 +_+ ，我們一般都是直接用現成的因子圖、圖優化方案，要創新可不容易，分享三川小哥的入坑指難。

102. 後端優化庫

• GTSAM：github.com/borglab/gtsa ；官網
• g2o：github.com/RainerKuemme
• ceres：ceres-solver.org/

103. ICE-BA

• 論文：Liu H, Chen M, Zhang G, et al. Ice-ba: Incremental, consistent and efficient bundle adjustment for visual-inertial slam[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 1974-1982.
• 代碼：github.com/baidu/ICE-BA

104. minisam（因子圖最小二乘優化架構）

• 論文：Dong J, Lv Z. miniSAM: A Flexible Factor Graph Non-linear Least Squares Optimization Framework[J]. arXiv preprint arXiv:1909.00903, 2019.
• 代碼：github.com/dongjing3309 ； 文檔

105. SA-SHAGO（幾何基元圖優化）

• 論文：Aloise I, Della Corte B, Nardi F, et al. Systematic Handling of Heterogeneous Geometric Primitives in Graph-SLAM Optimization[J]. IEEE Robotics and Automation Letters, 2019, 4(3): 2738-2745.
• 代碼：srrg.gitlab.io/sashago-

106. MH-iSAM2（SLAM 優化器）

• 論文：Hsiao M, Kaess M. MH-iSAM2: Multi-hypothesis iSAM using Bayes Tree and Hypo-tree[C]//2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019: 1274-1280.
• 代碼：bitbucket.org/rpl_cmu/m

107. MOLA（用于定位和建圖的子產品化優化架構）

• 論文：Blanco-Claraco J L. A Modular Optimization Framework for Localization and Mapping[J]. Proc. of Robotics: Science and Systems (RSS), FreiburgimBreisgau, Germany, 2019, 2.

首發于：2020 年 03 月 31 日

Email：[email protected]

更新日志：

2020.03.31 補充 +1：TUM Basalt ，分類在 Sensor Fusion 中；

2020.04.04 補充 +1：Limo，分類在 Sensor Fusion 中；

2020.04.04 補充 +1：DynSLAM，分類在 Dynamic SLAM 中；

2020.04.25 補充 +2：Map2DFusion、CCM-SLAM，分類在 Geometric SLAM 中；

2020.04.25 補充 +2：北航 LARVIO、浙大 vig-init，分類在 Sensor Fusion 中；

2020.04.25 補充 +2：GCNv2_SLAM、semantic_suma 分類在 Sematic/Deep SLAM；

2020.05.24 補充 +2：vilib、Kimera-VIO 分類在 Sensor Fusion；

2020.05.24 補充 +1：Voxgraph 分類在 Mapping；

2020.05.24 補充 +1：Neural-SLAM 分類在 Sematic/Deep SLAM；

2020.05.24 補充 +1：VPS-SLAM 分類在 Multi-Landmarks/Object SLAM；

2020.06.27 補充 +1：maplab 分了在 Sensor Fusion 中；

2020.06.27 補充 +1：SegMap 分了在 Mapping 中；

2020.07.27 補充 +1：ORB-SLAM3 分類在 Geometric SLAM 中（本文的第 100 項開源代碼的位置獻給 ORB-SLAM3 ）；

2020.08.27 補充 +1：Structure-SLAM-PointLine 分類在 Multi-Landmarks/Object SLAM 中；

2020.08.27 補充 +1：VDO-SLAM 分類在 Dynamic SLAM 中；

2021.02.14 補充 +1：OpenREALM 分類在 Mapping 中；

2021.02.14 補充 +1：PL-VINS 分類在 Multi-Landmarks/Object SLAM 中；

2021.02.14 補充 +2：lili-om、CamVox 分類在 Sensor Fusion 中；

2021.02.14 補充 +1：TartanVO 分類在 Semantic / Deep SLAM 中。