83 项开源视觉 SLAM 方案够你用了吗？
时间：2023-09-23 09:37:02
点击上方“3DCVer选择星标
第一时间送达干货
前言
1.本文由知乎作者小吴同学同步发布于https://zhuanlan.zhihu.com/p/11559978/并继续更新。
2.本文简要介绍了各种开源视觉SLAM方案如下7类别(虽然有很多文章不能适当分类):
·Geometric SLAM
·Semantic / Learning SLAM
·Multi-Landmarks / Object SLAM
·VIO / VISLAM
·Dynamic SLAM
·Mapping
·Optimization
3.由于本人自2019年3月开始整理，所以以下代码基本集中在经典框架之外19-20年；此外，个人更关注；VO、物体级SLAM和多路标SLAM，因此，以下内容收集不完整，不能覆盖视觉SLAM仅供参考。
一、Geometric SLAM（20项）
这一类是基于特征点、直接法或半直接法的传统SLAM，但是2019年也新诞生了9开源方案。
1. PTAM
论文：Klein G, Murray D.Parallel tracking and mapping for small AR workspaces[C]//Mixed andAugmented Reality, 2007. ISMAR 2007. 6th IEEE and ACM International Symposiumon. IEEE, 2007: 225-234.
代码：https://github.com/Oxford-PTAM/PTAM-GPL
工程地址：http://www.robots.ox.ac.uk/~gk/PTAM/
其他作者研究：http://www.robots.ox.ac.uk/~gk/publications.html
2. S-PTAM（双目PTAM）
论文：Taihú Pire,Thomas Fischer, Gastón Castro,Pablo De Cristóforis, Javier Civera and Julio Jacobo Berlles.S-PTAM: Stereo Parallel Tracking and Mapping. Robotics and AutonomousSystems, 2017.
代码：https://github.com/lrse/sptam
其他作者论文：Castro G,Nitsche M A, Pire T, et al.Efficient on-board Stereo SLAM throughconstrained-covisibility strategies[J]. Robotics and Autonomous Systems, 2019.
3. MonoSLAM
论文：Davison A J, Reid I D, Molton N D, et al.MonoSLAM:Real-time single camera SLAM[J]. IEEE transactions on patternanalysis and machine intelligence, 2007, 29(6): 1052-1067.
代码：https://github.com/hanmekim/SceneLib2
4. ORB-SLAM2
论文：Mur-Artal R, Tardós J D.Orb-slam2: Anopen-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEETransactions on Robotics, 2017, 33(5): 1255-1262.
代码：https://github.com/raulmur/ORB_SLAM2
其他作者论文：
单目半稠密建图：Mur-Artal R, Tardós J D.Probabilistic Semi-Dense Mapping from Highly AccurateFeature-Based Monocular SLAM[C]//Robotics: Science and Systems. 2015,2015.
VIORB：Mur-Artal R, Tardós J D.Visual-inertialmonocular SLAM with map reuse[J]. IEEE Robotics and AutomationLetters, 2017, 2(2): 796-803.
多地图：Elvira R, Tardós J D, Montiel J M M.ORBSLAM-Atlas: arobust and accurate multi-map system[J]. arXiv preprint arXiv:1908.11585, 2019.
以下5, 6, 7, 8几项是TUM全家桶的计算机视觉组
5. DSO
论文：Engel J, Koltun V, Cremers D.Direct sparseodometry[J]. IEEE transactions on pattern analysis and machineintelligence, 2017, 40(3): 611-625.
代码：https://github.com/JakobEngel/dso
双目DSO：Wang R, Schworer M, Cremers D.Stereo DSO: Large-scale direct sparse visual odometry withstereo cameras[C]//Proceedings of the IEEE International Conference onComputer Vision. 2017: 3903-3911.
VI-DSO：Von Stumberg L, Usenko V, Cremers D.Direct sparsevisual-inertial odometry using dynamic marginalization[C]//2018 IEEEInternational Conference on Robotics and Automation (ICRA). IEEE, 2018:2510-2517.
6. LDSO
高翔在DSO加闭环工作
论文：Gao X, Wang R, Demmel N, et al.LDSO: Directsparse odometry with loop closure[C]//2018 IEEE/RSJ InternationalConference on Intelligent Robots and Systems (IROS). IEEE, 2018:2198-2204.
代码：https://github.com/tu-vision/LDSO
7. LSD-SLAM
论文：Engel J, Schöps T, Cremers D. LSD-SLAM: Large-scale direct monocular SLAM[C]//Europeanconference on computer vision. Springer, Cham, 2014: 834-849.
代码：https://github.com/tum-vision/lsd_slam
8. DVO-SLAM
论文：Kerl C, Sturm J, Cremers D. Dense visualSLAM for RGB-D cameras[C]//2013 IEEE/RSJ International Conferenceon Intelligent Robots and Systems. IEEE, 2013: 2100-2106.
代码 1：https://github.com/tum-vision/dvo_slam
代码 2：https://github.com/tum-vision/dvo
其他论文：
Kerl C, Sturm J,Cremers D. Robust odometry estimation for RGB-D cameras[C]//2013 IEEEinternational 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 IEEEinternational conference on computer vision workshops (ICCV Workshops). IEEE, 2011:719-722.
9. SVO
苏黎世大学机器人与感知课题组
论文：Forster C, Pizzoli M, Scaramuzza D. SVO: Fast semi-direct monocular visual odometry[C]//2014 IEEEinternational conference on robotics and automation (ICRA). IEEE, 2014:15-22.
代码：https://github.com/uzh-rpg/rpg_svo
Forster C, ZhangZ, Gassner M, et al. SVO: Semidirect visual odometry for monocular andmulticamera systems[J]. IEEE Transactions on Robotics, 2016,33(2): 249-265.
10. DSM
论文：Zubizarreta J, Aguinaga I, Montiel J M M. Direct sparsemapping[J]. arXiv preprint arXiv:1904.06577, 2019.
代码：https://github.com/jzubizarreta/dsm
11. openvslam
论文：Sumikura S,Shibuya M, Sakurada K. OpenVSLAM: A Versatile Visual SLAM Framework[C]//Proceedingsof the 27th ACM International Conference on Multimedia. 2019: 2292-2295.
代码：https://github.com/xdspacelab/openvslam
12. se2lam（地面车辆位姿估计的视觉里程计）
论文：Zheng F, Liu Y H. Visual-OdometricLocalization and Mapping for Ground Vehicles Using SE (2)-XYZ Constraints[C]//2019International Conference on Robotics and Automation (ICRA). IEEE, 2019:3556-3562.
代码：https://github.com/izhengfan/se2lam
作者的另外一项工作
论文：Zheng F, Tang H,Liu Y H. Odometry-vision-basedground vehicle motion estimation with se (2)-constrained se (3) poses[J]. IEEEtransactions on cybernetics, 2018, 49(7): 2652-2663.
代码：https://github.com/izhengfan/se2clam
13. GraphSfM（基于图的并行大尺度 SFM）
论文：Chen Y, Shen S,Chen Y, et al. Graph-BasedParallel Large Scale Structure from Motion[J]. arXivpreprint arXiv:1912.10659, 2019.
代码：https://github.com/AIBluefisher/GraphSfM
14. LCSD_SLAM（松耦合的半直接法单目 SLAM）
论文：Lee S H, Civera J. Loosely-Coupledsemi-direct monocular SLAM[J]. IEEE Robotics and AutomationLetters, 2018, 4(2): 399-406.
代码：https://github.com/sunghoon031/LCSD_SLAM；谷歌学术 ；演示视频
作者另外一篇关于单目尺度的文章代码开源：Lee S H, deCroon G. Stability-based scale estimation for monocular SLAM[J]. IEEERobotics and Automation Letters, 2018, 3(2): 780-787.
15. RESLAM（基于边的 SLAM）
论文：Schenk F, Fraundorfer F. RESLAM: Areal-time robust edge-based SLAM system[C]//2019 International Conference onRobotics and Automation (ICRA). IEEE, 2019: 154-160.
代码：https://github.com/fabianschenk/RESLAM
16. scale_optimization（将单目 DSO 拓展到双目）
论文：Mo J, Sattar J. ExtendingMonocular Visual Odometry to Stereo Camera System by Scale Optimization[C].International Conference on Intelligent Robots and Systems (IROS), 2019.
代码：https://github.com/jiawei-mo/scale_optimization
17. BAD-SLAM（直接法 RGB-D SLAM）
论文：Schops T, Sattler T, Pollefeys M. BAD SLAM: Bundle Adjusted Direct RGB-D SLAM[C]//Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition. 2019:134-144.
代码：https://github.com/ETH3D/badslam
18. GSLAM（集成 ORB-SLAM2，DSO，SVO 的通用框架）
论文：Zhao Y, Xu S, Bu S, et al. GSLAM: A general SLAM framework and benchmark[C]//Proceedingsof the IEEE International Conference on Computer Vision. 2019:1110-1120.
代码：https://github.com/zdzhaoyong/GSLAM
19. ARM-VO（运行于 ARM 处理器上的单目 VO）
论文：Nejad Z Z, Ahmadabadian A H. ARM-VO: an efficient monocular visual odometry for groundvehicles on ARM CPUs[J]. Machine Vision and Applications, 2019:1-10.
代码：https://github.com/zanazakaryaie/ARM-VO
20. cvo-rgbd（直接法 RGB-D VO）
论文：Ghaffari M, Clark W, Bloch A, et al. ContinuousDirect Sparse Visual Odometry from RGB-D Images[J]. arXivpreprint arXiv:1904.02266, 2019.
代码：https://github.com/MaaniGhaffari/cvo-rgbd
二、Semantic / Learning SLAM（12 项）
SLAM 与深度学习相结合的工作当前主要体现在两个方面，一方面是将语义信息参与到建图、位姿估计等环节中，另一方面是端到端地完成 SLAM 的某一个步骤（比如 VO，闭环等）。个人对后者没太关注，也同样欢迎大家在issue中分享。
21. MsakFusion
论文：Runz M, Buffier M, Agapito L. Maskfusion:Real-time recognition, tracking and reconstruction of multiple moving objects[C]//2018 IEEEInternational Symposium on Mixed and Augmented Reality (ISMAR). IEEE, 2018:10-20.
代码：https://github.com/martinruenz/maskfusion
22. SemanticFusion
论文：McCormac J, Handa A, Davison A, et al. Semanticfusion:Dense 3d semantic mapping with convolutional neural networks[C]//2017 IEEEInternational Conference on Robotics and automation (ICRA). IEEE, 2017:4628-4635.
代码：https://github.com/seaun163/semanticfusion
23. semantic_3d_mapping
论文：Yang S, Huang Y, Scherer S. Semantic 3Doccupancy mapping through efficient high order CRFs[C]//2017IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).IEEE, 2017: 590-597.
代码：https://github.com/shichaoy/semantic_3d_mapping
24. Kimera（实时度量与语义定位建图开源库）
论文：Rosinol A, AbateM, Chang Y, et al. Kimera: anOpen-Source Library for Real-Time Metric-Semantic Localization and Mapping[J]. arXivpreprint arXiv:1910.02490, 2019.
代码：https://github.com/MIT-SPARK/Kimera
25. NeuroSLAM（脑启发式 SLAM）
论文：Yu F, Shang J, Hu Y, et al. NeuroSLAM: a brain-inspired SLAM system for 3Denvironments[J]. Biological Cybernetics, 2019: 1-31.
代码：https://github.com/cognav/NeuroSLAM
第四作者就是 Rat SLAM 的作者，文章也比较了十余种脑启发式的 SLAM
26. gradSLAM（自动分区的稠密 SLAM）
论文：Jatavallabhula K M, Iyer G, Paull L. gradSLAM:Dense SLAM meets Automatic Differentiation[J]. arXivpreprint arXiv:1910.10672, 2019.
代码（预计 20 年 4 月放出）：https://github.com/montrealrobotics/gradSLAM
27. ORB-SLAM2 + 目标检测/分割的方案语义建图
https://github.com/floatlazer/semantic_slam
https://github.com/qixuxiang/orb-slam2_with_semantic_labelling
https://github.com/Ewenwan/ORB_SLAM2_SSD_Semantic
28. SIVO（语义辅助特征选择）
论文：Ganti P, Waslander S. NetworkUncertainty Informed Semantic Feature Selection for Visual SLAM[C]//2019 16thConference on Computer and Robot Vision (CRV). IEEE, 2019: 121-128.
代码：https://github.com/navganti/SIVO
29. FILD（临近图增量式闭环检测）
论文：Shan An, Guangfu Che, Fangru Zhou,Xianglong Liu, Xin Ma, Yu Chen.Fast and Incremental Loop Closure Detection usingProximity Graphs. pp. 378-385, The 2019 IEEE/RSJ International Conferenceon Intelligent Robots and Systems (IROS2019)
代码：https://github.com/AnshanTJU/FILD
30. object-detection-sptam（目标检测与双目 SLAM）
论文：Pire T, Corti J, Grinblat G. Online Object Detection and Localization on Stereo VisualSLAM System[J]. Journal of Intelligent & Robotic Systems, 2019:1-10.
代码：https://github.com/CIFASIS/object-detection-sptam
31. Map Slammer（单目深度估计 + SLAM）
论文：Torres-Camara J M, Escalona F, Gomez-DonosoF, et al. Map Slammer: Densifying Scattered KSLAM 3D Maps withEstimated Depth[C]//Iberian Robotics conference. Springer, Cham, 2019:563-574.
代码：https://github.com/jmtc7/mapSlammer
32. NOLBO（变分模型的概率 SLAM）
论文：Yu H, Lee B. Not Only LookBut Observe: Variational Observation Model of Scene-Level 3D Multi-ObjectUnderstanding for Probabilistic SLAM[J]. arXiv preprint arXiv:1907.09760, 2019.
代码：https://github.com/bogus2000/NOLBO
三、Multi-Landmarks / Object SLAM（12 项）
其实多路标的点、线、平面 SLAM 和物体级 SLAM 完全可以分类在 Geometric SLAM 和 Semantic SLAM 中，但个人对这一方向比较感兴趣（也是我的研究生课题），所以将其独立出来，开源方案相对较少，但很有意思。
33. PL-SVO（点线 SVO）
论文：Gomez-Ojeda R, Briales J, Gonzalez-JimenezJ. PL-SVO: Semi-direct Monocular Visual Odometry by combiningpoints and line segments[C]//Intelligent Robots and Systems(IROS), 2016 IEEE/RSJ International Conference on. IEEE, 2016:4211-4216.
代码：https://github.com/rubengooj/pl-svo
34. stvo-pl（双目点线 VO）
论文：Gomez-Ojeda R, Gonzalez-Jimenez J. Robust stereo visual odometry through a probabilisticcombination of points and line segments[C]//2016 IEEE International Conferenceon Robotics and Automation (ICRA). IEEE, 2016: 2521-2526.
代码：https://github.com/rubengooj/stvo-pl
35. PL-SLAM（点线 SLAM）
论文：Gomez-Ojeda R, Zuñiga-Noël D, Moreno F A,et al. PL-SLAM: aStereo SLAM System through the Combination of Points and Line Segments[J]. arXivpreprint arXiv:1705.09479, 2017.
代码：https://github.com/rubengooj/pl-slam
Gomez-Ojeda R,Moreno F A, Zuñiga-Noël D, et al.PL-SLAM: a stereo SLAM system through the combination ofpoints and line segments[J]. IEEE Transactions on Robotics, 2019,35(3): 734-746.
36. PL-VIO
论文：He Y, Zhao J, Guo Y, et al. PL-VIO:Tightly-coupled monocular visual–inertial odometry using point and linefeatures[J]. Sensors, 2018, 18(4): 1159.
代码：https://github.com/HeYijia/PL-VIO
VINS + 线段：https://github.com/Jichao-Peng/VINS-Mono-Optimization
37. lld-slam（用于 SLAM 的可学习型线段描述符）
论文：Vakhitov A, Lempitsky V. Learnable line segment descriptor for visual SLAM[J]. IEEEAccess, 2019, 7: 39923-39934.
代码：https://github.com/alexandervakhitov/lld-slam；Video
点线结合的工作还有很多，国内的比如 + 上交邹丹平老师的 Zou D, Wu Y, Pei L, et al. StructVIO:visual-inertial odometry with structural regularity of man-made environments[J]. IEEETransactions on Robotics, 2019, 35(4): 999-1013. + 浙大的 Zuo X, Xie X, Liu Y, et al. Robust visualSLAM with point and line features[C]//2017 IEEE/RSJ InternationalConference on Intelligent Robots and Systems (IROS). IEEE, 2017:1775-1782.
38. PlaneSLAM
论文：Wietrzykowski J. On the representation of planes for efficient graph-basedslam with high-level features[J]. Journal of Automation MobileRobotics and Intelligent Systems, 2016, 10.
代码：https://github.com/LRMPUT/PlaneSLAM
作者另外一项开源代码，没有找到对应的论文：https://github.com/LRMPUT/PUTSLAM
39. Eigen-Factors（特征因子平面对齐）
论文：Ferrer G. Eigen-Factors: Plane Estimation for Multi-Frame andTime-Continuous Point Cloud Alignment[C]//2019 IEEE/RSJ InternationalConference on Intelligent Robots and Systems (IROS). IEEE, 2019:1278-1284.
代码：https://gitlab.com/gferrer/eigen-factors-iros2019
40. PlaneLoc
论文：Wietrzykowski J, Skrzypczyński P. PlaneLoc:Probabilistic global localization in 3-D using local planar features[J]. Roboticsand Autonomous Systems, 2019, 113: 160-173.
代码：https://github.com/LRMPUT/PlaneLoc
41. Pop-up SLAM
论文：Yang S, Song Y, Kaess M, et al. Pop-up slam:Semantic monocular plane slam for low-texture environments[C]//2016IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).IEEE, 2016: 1222-1229.
代码：https://github.com/shichaoy/pop_up_slam
42. Object SLAM
论文：Mu B, Liu S Y, Paull L, et al. Slam withobjects using a nonparametric pose graph[C]//2016 IEEE/RSJ InternationalConference on Intelligent Robots and Systems (IROS). IEEE, 2016:4602-4609.
代码：https://github.com/BeipengMu/objectSLAM
43. voxblox-plusplus（物体级体素建图）
论文：Grinvald M, Furrer F, Novkovic T, et al. Volumetricinstance-aware semantic mapping and 3D object discovery[J]. IEEERobotics and Automation Letters, 2019, 4(3): 3037-3044.
代码：https://github.com/ethz-asl/voxblox-plusplus
44. Cube SLAM
论文：Yang S, Scherer S. Cubeslam:Monocular 3-d object slam[J]. IEEE Transactions on Robotics, 2019,35(4): 925-938.
代码：https://github.com/shichaoy/cube_slam
也有很多有意思的但没开源的物体级 SLAM
Ok K, Liu K,Frey K, et al. RobustObject-based SLAM for High-speed Autonomous Navigation[C]//2019International Conference on Robotics and Automation (ICRA). IEEE, 2019:669-675.
Li J, Meger D,Dudek G. SemanticMapping for View-Invariant Relocalization[C]//2019International 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]. IEEERobotics and Automation Letters, 2018, 4(1): 1-8.
四、VIO / VISLAM（10 项）
在传感器融合方面只关注了视觉 + 惯导，其他传感器像 LiDAR，GPS 关注较少（SLAM 太复杂啦 -_-! ）。视惯融合的新工作也相对较少，基本一些经典的方案就够用了。
45. msckf_vio
论文：Sun K, Mohta K, Pfrommer B, et al. Robust stereovisual inertial odometry for fast autonomous flight[J]. IEEERobotics and Automation Letters, 2018, 3(2): 965-972.
代码：https://github.com/KumarRobotics/msckf_vio
46. rovio
论文：Bloesch M, Omari S, Hutter M, et al. Robust visual inertial odometry using a direct EKF-basedapproach[C]//2015 IEEE/RSJ international conference onintelligent robots and systems (IROS). IEEE, 2015: 298-304.
代码：https://github.com/ethz-asl/rovio
47. R-VIO
论文：Huai Z, Huang G. Robocentricvisual-inertial odometry[C]//2018 IEEE/RSJ InternationalConference on Intelligent Robots and Systems (IROS). IEEE, 2018:6319-6326.
代码：https://github.com/rpng/R-VIO
48. okvis
论文：Leutenegger S, Lynen S, Bosse M, et al. Keyframe-based visual–inertial odometry using nonlinearoptimization[J]. The International Journal of Robotics Research, 2015,34(3): 314-334.
代码：https://github.com/ethz-asl/okvis
49. VIORB
论文：Mur-Artal R, Tardós J D. Visual-inertialmonocular SLAM with map reuse[J]. IEEE Robotics and AutomationLetters, 2017, 2(2): 796-803.
代码：https://github.com/jingpang/LearnVIORB（VIORB 本身是没有开源的，这是王京大佬复现的一个版本）
50. VINS-mono
论文：Qin T, Li P, Shen S. Vins-mono: Arobust and versatile monocular visual-inertial state estimator[J]. IEEETransactions on Robotics, 2018, 34(4): 1004-1020.
代码：https://github.com/HKUST-Aerial-Robotics/VINS-Mono
双目版 VINS-Fusion：https://github.com/HKUST-Aerial-Robotics/VINS-Fusion
移动段 VINS-mobile：https://github.com/HKUST-Aerial-Robotics/VINS-Mobile
51. VINS-RGBD
论文：Shan Z, Li R, Schwertfeger S. RGBD-InertialTrajectory Estimation and Mapping for Ground Robots[J]. Sensors, 2019,19(10): 2251.
代码：https://github.com/STAR-Center/VINS-RGBD
52. Open-VINS
论文：Geneva P, Eckenhoff K, Lee W, et al. Openvins: A research platform for visual-inertialestimation[C]//IROS 2019 Workshop on Visual-Inertial Navigation:Challenges and Applications, Macau, China. IROS 2019.
代码：https://github.com/rpng/open_vins
53. versavis（多功能的视惯传感器系统）
论文：Tschopp F, RinerM, Fehr M, et al. VersaVIS—AnOpen Versatile Multi-Camera Visual-Inertial Sensor Suite[J]. Sensors, 2020,20(5): 1439.
代码：https://github.com/ethz-asl/versavis
54. CPI（视惯融合的封闭式预积分）
论文：Eckenhoff K, Geneva P, Huang G. Closed-form preintegration methods for graph-basedvisual–inertial navigation[J]. The International Journal ofRobotics Research, 2018.
代码：https://github.com/rpng/cpi
五、Dynamic SLAM（5 项）
动态 SLAM 也是一个很值得研究的话题，这里不太好分类，很多工作用到了语义信息或者用来三维重建，收集的方案相对较少，欢迎补充issue。
55. DynamicSemanticMapping（动态语义建图）
论文：Kochanov D, Ošep A, Stückler J, et al. Scene flow propagation for semantic mapping and objectdiscovery in dynamic street scenes[C]//Intelligent Robots and Systems(IROS), 2016 IEEE/RSJ International Conference on. IEEE, 2016:1785-1792.
代码：https://github.com/ganlumomo/DynamicSemanticMapping
56. DS-SLAM（动态语义 SLAM）
论文：Yu C, Liu Z, Liu X J, et al. DS-SLAM: Asemantic visual SLAM towards dynamic environments[C]//2018IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).IEEE, 2018: 1168-1174.
代码：https://github.com/ivipsourcecode/DS-SLAM
57. Co-Fusion（实时分割与跟踪多物体）
论文：Rünz M, Agapito L. Co-fusion:Real-time segmentation, tracking and fusion of multiple objects[C]//2017 IEEEInternational Conference on Robotics and Automation (ICRA). IEEE, 2017:4471-4478.
代码：https://github.com/martinruenz/co-fusion
58. DynamicFusion
论文：Newcombe R A, Fox D, Seitz S M. Dynamicfusion: Reconstruction and tracking of non-rigidscenes in real-time[C]//Proceedings of the IEEE conference oncomputer vision and pattern recognition. 2015: 343-352.
代码：https://github.com/mihaibujanca/dynamicfusion
59. ReFusion（动态场景利用残差三维重建）
论文：Palazzolo E, Behley J, Lottes P, et al. ReFusion: 3DReconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals[J]. arXivpreprint arXiv:1905.02082, 2019.
代码：https://github.com/PRBonn/refusion
六、Mapping（18 项）
针对建图的工作一方面是利用几何信息进行稠密重建，另一方面很多工作利用语义信息达到了很好的语义重建效果，三维重建本身就是个很大的话题，开源代码也很多，以下方案收集地可能也不太全。
60. InfiniTAM（跨平台 CPU 实时重建）
论文：Prisacariu V A,Kähler O, Golodetz S, et al. Infinitam v3: A framework for large-scale 3dreconstruction with loop closure[J]. arXiv preprint arXiv:1708.00783, 2017.
代码：https://github.com/victorprad/InfiniTAM
61. BundleFusion
论文：Dai A, Nießner M, Zollhöfer M, et al. Bundlefusion:Real-time globally consistent 3d reconstruction using on-the-fly surfacereintegration[J]. ACM Transactions on Graphics (TOG), 2017,36(4): 76a.
代码：https://github.com/niessner/BundleFusion
62. KinectFusion
论文：Newcombe R A, Izadi S, Hilliges O, et al. KinectFusion: Real-time dense surface mapping and tracking[C]//2011 10thIEEE International Symposium on Mixed and Augmented Reality. IEEE, 2011:127-136.
代码：https://github.com/chrdiller/KinectFusionApp
63. ElasticFusion
论文：Whelan T, Salas-Moreno R F, Glocker B, etal. ElasticFusion: Real-time dense SLAM and light sourceestimation[J]. The International Journal of Robotics Research, 2016,35(14): 1697-1716.
代码：https://github.com/mp3guy/ElasticFusion
64. Kintinuous
ElasticFusion 同一个团队的工作，帝国理工 Stefan Leutenegger
论文：Whelan T, Kaess M, Johannsson H, et al. Real-time large-scale dense RGB-D SLAM with volumetricfusion[J]. The International Journal of Robotics Research, 2015,34(4-5): 598-626.
代码：https://github.com/mp3guy/Kintinuous
65. ElasticReconstruction
论文：Choi S, Zhou Q Y, Koltun V. Robust reconstruction of indoor scenes[C]//Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition. 2015:5556-5565.
代码：https://github.com/qianyizh/ElasticReconstruction
66. FlashFusion
论文：Han L, Fang L. FlashFusion:Real-time Globally Consistent Dense 3D Reconstruction using CPU Computing[C]. RSS, 2018.
代码（一直没放出来）：https://github.com/lhanaf/FlashFusion
67. RTAB-Map（激光视觉稠密重建）
论文：Labbé M, Michaud F. RTAB‐Map as an open‐source lidar and visual simultaneouslocalization and mapping library for large‐scale and long‐term online operation[J]. Journal ofField Robotics, 2019, 36(2): 416-446.
代码：https://github.com/introlab/rtabmap
68. RobustPCLReconstruction（户外稠密重建）
论文：Lan Z, Yew Z J, Lee G H. Robust Point Cloud Based Reconstruction of Large-ScaleOutdoor Scenes[C]//Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition. 2019: 9690-9698.
代码：https://github.com/ziquan111/RobustPCLReconstruction
69. plane-opt-rgbd（室内平面重建）
论文：Wang C, Guo X. Efficient Plane-Based Optimization of Geometry and Texturefor Indoor RGB-D Reconstruction[C]//Proceedings of the IEEE Conferenceon Computer Vision and Pattern Recognition Workshops. 2019: 49-53.
代码：https://github.com/chaowang15/plane-opt-rgbd
70. DenseSurfelMapping（稠密表面重建）
论文：Wang K, Gao F, Shen S. Real-timescalable dense surfel mapping[C]//2019 International Conference onRobotics and Automation (ICRA). IEEE, 2019: 6919-6925.
代码：https://github.com/HKUST-Aerial-Robotics/DenseSurfelMapping
71. surfelmeshing（网格重建）
论文：Schöps T, Sattler T, Pollefeys M. Surfelmeshing:Online surfel-based mesh reconstruction[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence, 2019.
代码：https://github.com/puzzlepaint/surfelmeshing
72. DPPTAM（单目稠密重建）
论文：Concha Belenguer A, Civera Sancho J. DPPTAM: Dense piecewise planar tracking and mapping from amonocular sequence[C]//Proc. IEEE/RSJ Int. Conf. Intell. Rob. Syst. 2015(ART-2015-92153).
代码：https://github.com/alejocb/dpptam
相关研究：基于超像素的单目 SLAM：UsingSuperpixels in Monocular SLAM ICRA 2014 ；谷歌学术
73. VI-MEAN（单目视惯稠密重建）
论文：Yang Z, Gao F, Shen S. Real-time monocular dense mapping on aerial robots usingvisual-inertial fusion[C]//2017 IEEE International Conference onRobotics and Automation (ICRA). IEEE, 2017: 4552-4559.
代码：https://github.com/dvorak0/VI-MEAN
74. REMODE（单目概率稠密重建）
论文：Pizzoli M, Forster C, Scaramuzza D. REMODE: Probabilistic, monocular dense reconstruction inreal time[C]//2014 IEEE International Conference on Robotics andAutomation (ICRA). IEEE, 2014: 2609-2616.
原始开源代码：https://github.com/uzh-rpg/rpg_open_remode
与 ORB-SLAM2 结合版本：https://github.com/ayushgaud/ORB_SLAM2https://github.com/ayushgaud/ORB_SLAM2
75. DeepFactors（实时的概率单目稠密 SLAM）
帝国理工学院戴森机器人实验室
论文：Czarnowski J, Laidlow T, Clark R, et al. DeepFactors:Real-Time Probabilistic Dense Monocular SLAM[J]. arXivpreprint arXiv:2001.05049, 2020.
代码：https://github.com/jczarnowski/DeepFactors（还未放出）
其他论文：Bloesch M,Czarnowski J, Clark R, et al. CodeSLAM—learning a compact, optimisable representationfor dense visual SLAM[C]//Proceedings of the IEEE conference oncomputer vision and pattern recognition. 2018: 2560-2568.
76. probabilistic_mapping（单目概率稠密重建）
港科沈邵劼老师团队
论文：Ling Y, Wang K, Shen S. Probabilisticdense reconstruction from a moving camera[C]//2018IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).IEEE, 2018: 6364-6371.
代码：https://github.com/ygling2008/probabilistic_mapping
另外一篇稠密重建文章的代码一直没放出来Github：Ling Y, Shen S. Real‐timedense mapping for online processing and navigation[J]. Journal ofField Robotics, 2019, 36(5): 1004-1036.
77. ORB-SLAM2 单目半稠密建图
论文：Mur-Artal R, Tardós J D. Probabilistic Semi-Dense Mapping from Highly AccurateFeature-Based Monocular SLAM[C]//Robotics: Science and Systems. 2015,2015.
代码（本身没有开源，贺博复现的一个版本）：https://github.com/HeYijia/ORB_SLAM2
加上线段之后的半稠密建图
论文：He S, Qin X, Zhang Z, et al. Incremental3d line segment extraction from semi-dense slam[C]//2018 24thInternational Conference on Pattern Recognition (ICPR). IEEE, 2018:1658-1663.
代码：https://github.com/shidahe/semidense-lines
作者在此基础上用于指导远程抓取操作的一项工作：https://github.com/atlas-jj/ORB-SLAM-free-space-carving
七、Optimization（6 项）
个人感觉优化可能是 SLAM 中最难的一部分了吧 +_+ ，我们一般都是直接用现成的因子图、图优化方案，要创新可不容易，分享山川小哥d的入坑指南https://zhuanlan.zhihu.com/p/53972892。
78. 后端优化库
GTSAM：https://github.com/borglab/gtsam
g2o：https://github.com/RainerKuemmerle/g2o
ceres：http://ceres-solver.org/
79. ICE-BA
论文：Liu H, Chen M, Zhang G, et al. Ice-ba: Incremental, consistent and efficient bundleadjustment for visual-inertial slam[C]//Proceedings of the IEEE Conferenceon Computer Vision and Pattern Recognition. 2018: 1974-1982.
代码：https://github.com/baidu/ICE-BA
80. minisam（因子图最小二乘优化框架）
论文：Dong J, Lv Z. miniSAM: AFlexible Factor Graph Non-linear Least Squares Optimization Framework[J]. arXivpreprint arXiv:1909.00903, 2019.
代码：https://github.com/dongjing3309/minisam
81. SA-SHAGO（几何基元图优化）
论文：Aloise I, Della Corte B, Nardi F, et al. Systematic Handling of Heterogeneous Geometric Primitivesin Graph-SLAM Optimization[J]. IEEE Robotics and AutomationLetters, 2019, 4(3): 2738-2745.
代码：https://srrg.gitlab.io/sashago-website/index.html#
82. MH-iSAM2（SLAM 优化器）
论文：Hsiao M, Kaess M. MH-iSAM2:Multi-hypothesis iSAM using Bayes Tree and Hypo-tree[C]//2019International Conference on Robotics and Automation (ICRA). IEEE, 2019:1274-1280.
代码：https://bitbucket.org/rpl_cmu/mh-isam2_lib/src/master/
83. MOLA（用于定位和建图的模块化优化框架）
论文：Blanco-Claraco J L. A ModularOptimization Framework for Localization and Mapping[J]. Proc. ofRobotics: Science and Systems (RSS), FreiburgimBreisgau, Germany, 2019,2.
代码：https://github.com/MOLAorg/mola
前言
1. 本文由知乎作者小吴同学同步发布于https://zhuanlan.zhihu.com/p/115599978/并持续更新。
2. 本文简单将各种开源视觉SLAM方案分为以下 7 类（固然有不少文章无法恰当分类）：
·Geometric SLAM
·Semantic / Learning SLAM
·Multi-Landmarks / Object SLAM
·VIO / VISLAM
·Dynamic SLAM
·Mapping
·Optimization
3. 由于本人自 2019 年 3 月开始整理，所以以下的代码除了经典的框架之外基本都集中在 19-20 年；此外个人比较关注 VO、物体级 SLAM 和多路标 SLAM，所以以下内容收集的也不完整，无法涵盖视觉 SLAM 的所有研究，仅作参考。
一、Geometric SLAM（20 项）
这一类是传统的基于特征点、直接法或半直接法的 SLAM，虽说传统，但 2019 年也新诞生了 9 个开源方案。
1. PTAM
论文：Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C]//Mixed andAugmented Reality, 2007. ISMAR 2007. 6th IEEE and ACM International Symposiumon. IEEE, 2007: 225-234.
代码：https://github.com/Oxford-PTAM/PTAM-GPL
工程地址：http://www.robots.ox.ac.uk/~gk/PTAM/
作者其他研究：http://www.robots.ox.ac.uk/~gk/publications.html
2. S-PTAM（双目 PTAM）
论文：Taihú Pire,Thomas Fischer, Gastón Castro,Pablo De Cristóforis, Javier Civera and Julio Jacobo Berlles. S-PTAM: Stereo Parallel Tracking and Mapping. Robotics and AutonomousSystems, 2017.
代码：https://github.com/lrse/sptam
作者其他论文：Castro G,Nitsche M A, Pire T, et al. Efficient on-board Stereo SLAM throughconstrained-covisibility strategies[J]. Robotics and Autonomous Systems, 2019.
3. MonoSLAM
论文：Davison A J, Reid I D, Molton N D, et al. MonoSLAM:Real-time single camera SLAM[J]. IEEE transactions on patternanalysis and machine intelligence, 2007, 29(6): 1052-1067.
代码：https://github.com/hanmekim/SceneLib2
4. ORB-SLAM2
论文：Mur-Artal R, Tardós J D. Orb-slam2: Anopen-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEETransactions on Robotics, 2017, 33(5): 1255-1262.
代码：https://github.com/raulmur/ORB_SLAM2
作者其他论文：
单目半稠密建图：Mur-Artal R, Tardós J D. Probabilistic Semi-Dense Mapping from Highly AccurateFeature-Based Monocular SLAM[C]//Robotics: Science and Systems. 2015,2015.
VIORB：Mur-Artal R, Tardós J D. Visual-inertialmonocular SLAM with map reuse[J]. IEEE Robotics and AutomationLetters, 2017, 2(2): 796-803.
多地图：Elvira R, Tardós J D, Montiel J M M. ORBSLAM-Atlas: arobust and accurate multi-map system[J]. arXiv preprint arXiv:1908.11585, 2019.
以下 5, 6, 7, 8 几项是 TUM 计算机视觉组全家桶
5. DSO
论文：Engel J, Koltun V, Cremers D. Direct sparseodometry[J]. IEEE transactions on pattern analysis and machineintelligence, 2017, 40(3): 611-625.
代码：https://github.com/JakobEngel/dso
双目 DSO：Wang R, Schworer M, Cremers D. Stereo DSO: Large-scale direct sparse visual odometry withstereo cameras[C]//Proceedings of the IEEE International Conference onComputer Vision. 2017: 3903-3911.
VI-DSO：Von Stumberg L, Usenko V, Cremers D. Direct sparsevisual-inertial odometry using dynamic marginalization[C]//2018 IEEEInternational Conference on Robotics and Automation (ICRA). IEEE, 2018:2510-2517.
6. LDSO
高翔在 DSO 上添加闭环的工作
论文：Gao X, Wang R, Demmel N, et al. LDSO: Directsparse odometry with loop closure[C]//2018 IEEE/RSJ InternationalConference on Intelligent Robots and Systems (IROS). IEEE, 2018:2198-2204.
代码：https://github.com/tum-vision/LDSO
7. LSD-SLAM
论文：Engel J, Schöps T, Cremers D. LSD-SLAM: Large-scale direct monocular SLAM[C]//Europeanconference on computer vision. Springer, Cham, 2014: 834-849.
代码：https://github.com/tum-vision/lsd_slam
8. DVO-SLAM
论文：Kerl C, Sturm J, Cremers D. Dense visualSLAM for RGB-D cameras[C]//2013 IEEE/RSJ International Conferenceon Intelligent Robots and Systems. IEEE, 2013: 2100-2106.
代码 1：https://github.com/tum-vision/dvo_slam
代码 2：https://github.com/tum-vision/dvo
其他论文：
Kerl C, Sturm J,Cremers D. Robust odometry estimation for RGB-D cameras[C]//2013 IEEEinternational 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 IEEEinternational conference on computer vision workshops (ICCV Workshops). IEEE, 2011:719-722.
9. SVO
苏黎世大学机器人与感知课题组
论文：Forster C, Pizzoli M, Scaramuzza D. SVO: Fast semi-direct monocular visual odometry[C]//2014 IEEEinternational conference on robotics and automation (ICRA). IEEE, 2014:15-22.
代码：https://github.com/uzh-rpg/rpg_svo
Forster C, ZhangZ, Gassner M, et al. SVO: Semidirect visual odometry for monocular andmulticamera systems[J]. IEEE Transactions on Robotics, 2016,33(2): 249-265.
10. DSM
论文：Zubizarreta J, Aguinaga I, Montiel J M M. Direct sparsemapping[J]. arXiv preprint arXiv:1904.06577, 2019.
代码：https://github.com/jzubizarreta/dsm
11. openvslam
论文：Sumikura S,Shibuya M, Sakurada K. OpenVSLAM: A Versatile Visual SLAM Framework[C]//Proceedingsof the 27th ACM International Conference on Multimedia. 2019: 2292-2295.
代码：https://github.com/xdspacelab/openvslam
12. se2lam（地面车辆位姿估计的视觉里程计）
论文：Zheng F, Liu Y H. Visual-OdometricLocalization and Mapping for Ground Vehicles Using SE (2)-XYZ Constraints[C]//2019International Conference on Robotics and Automation (ICRA). IEEE, 2019:3556-3562.
代码：https://github.com/izhengfan/se2lam
作者的另外一项工作
论文：Zheng F, Tang H,Liu Y H. Odometry-vision-basedground vehicle motion estimation with se (2)-constrained se (3) poses[J]. IEEEtransactions on cybernetics, 2018, 49(7): 2652-2663.
代码：https://github.com/izhengfan/se2clam
13. GraphSfM（基于图的并行大尺度 SFM）
论文：Chen Y, Shen S,Chen Y, et al. Graph-BasedParallel Large Scale Structure from Motion[J]. arXivpreprint arXiv:1912.10659, 2019.
代码：https://github.com/AIBluefisher/GraphSfM
14. LCSD_SLAM（松耦合的半直接法单目 SLAM）
论文：Lee S H, Civera J. Loosely-Coupledsemi-direct monocular SLAM[J]. IEEE Robotics and AutomationLetters, 2018, 4(2): 399-406.
代码：https://github.com/sunghoon031/LCSD_SLAM；谷歌学术 ；演示视频
作者另外一篇关于单目尺度的文章代码开源：Lee S H, deCroon G. Stability-based scale estimation for monocular SLAM[J]. IEEERobotics and Automation Letters, 2018, 3(2): 780-787.
15. RESLAM（基于边的 SLAM）
论文：Schenk F, Fraundorfer F. RESLAM: Areal-time robust edge-based SLAM system[C]//2019 International Conference onRobotics and Automation (ICRA). IEEE, 2019: 154-160.
代码：https://github.com/fabianschenk/RESLAM
16. scale_optimization（将单目 DSO 拓展到双目）
论文：Mo J, Sattar J. ExtendingMonocular Visual Odometry to Stereo Camera System by Scale Optimization[C].International Conference on Intelligent Robots and Systems (IROS), 2019.
代码：https://github.com/jiawei-mo/scale_optimization
17. BAD-SLAM（直接法 RGB-D SLAM）
论文：Schops T, Sattler T, Pollefeys M. BAD SLAM: Bundle Adjusted Direct RGB-D SLAM[C]//Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition. 2019:134-144.
代码：https://github.com/ETH3D/badslam
18. GSLAM（集成 ORB-SLAM2，DSO，SVO 的通用框架）
论文：Zhao Y, Xu S, Bu S, et al. GSLAM: A general SLAM framework and benchmark[C]//Proceedingsof the IEEE International Conference on Computer Vision. 2019:1110-1120.
代码：https://github.com/zdzhaoyong/GSLAM
19. ARM-VO（运行于 ARM 处理器上的单目 VO）
论文：Nejad Z Z, Ahmadabadian A H. ARM-VO: an efficient monocular visual odometry for groundvehicles on ARM CPUs[J]. Machine Vision and Applications, 2019:1-10.
代码：https://github.com/zanazakaryaie/ARM-VO
20. cvo-rgbd（直接法 RGB-D VO）
论文：Ghaffari M, Clark W, Bloch A, et al. ContinuousDirect Sparse Visual Odometry from RGB-D Images[J]. arXivpreprint arXiv:1904.02266, 2019.
代码：https://github.com/MaaniGhaffari/cvo-rgbd
二、Semantic / Learning SLAM（12 项）
SLAM 与深度学习相结合的工作当前主要体现在两个方面，一方面是将语义信息参与到建图、位姿估计等环节中，另一方面是端到端地完成 SLAM 的某一个步骤（比如 VO，闭环等）。个人对后者没太关注，也同样欢迎大家在issue中分享。
21. MsakFusion
论文：Runz M, Buffier M, Agapito L. Maskfusion:Real-time recognition, tracking and reconstruction of multiple moving objects[C]//2018 IEEEInternational Symposium on Mixed and Augmented Reality (ISMAR). IEEE, 2018:10-20.
代码：https://github.com/martinruenz/maskfusion
22. SemanticFusion
论文：McCormac J, Handa A, Davison A, et al. Semanticfusion:Dense 3d semantic mapping with convolutional neural networks[C]//2017 IEEEInternational Conference on Robotics and automation (ICRA). IEEE, 2017:4628-4635.
代码：https://github.com/seaun163/semanticfusion
23. semantic_3d_mapping
论文：Yang S, Huang Y, Scherer S. Semantic 3Doccupancy mapping through efficient high order CRFs[C]//2017IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).IEEE, 2017: 590-597.
代码：https://github.com/shichaoy/semantic_3d_mapping
24. Kimera（实时度量与语义定位建图开源库）
论文：Rosinol A, AbateM, Chang Y, et al. Kimera: anOpen-Source Library for Real-Time Metric-Semantic Localization and Mapping[J]. arXivpreprint arXiv:1910.02490, 2019.
代码：https://github.com/MIT-SPARK/Kimera
25. NeuroSLAM（脑启发式 SLAM）
论文：Yu F, Shang J, Hu Y, et al. NeuroSLAM: a brain-inspired SLAM system for 3Denvironments[J]. Biological Cybernetics, 2019: 1-31.
代码：https://github.com/cognav/NeuroSLAM
第四作者就是 Rat SLAM 的作者，文章也比较了十余种脑启发式的 SLAM
26. gradSLAM（自动分区的稠密 SLAM）
论文：Jatavallabhula K M, Iyer G, Paull L. gradSLAM:Dense SLAM meets Automatic Differentiation[J]. arXivpreprint arXiv:1910.10672, 2019.
代码（预计 20 年 4 月放出）：https://github.com/montrealrobotics/gradSLAM
27. ORB-SLAM2 + 目标检测/分割的方案语义建图
https://github.com/floatlazer/semantic_slam
https://github.com/qixuxiang/orb-slam2_with_semantic_labelling
https://github.com/Ewenwan/ORB_SLAM2_SSD_Semantic
28. SIVO（语义辅助特征选择）
论文：Ganti P, Waslander S. NetworkUncertainty Informed Semantic Feature Selection for Visual SLAM[C]//2019 16thConference on Computer and Robot Vision (CRV). IEEE, 2019: 121-128.
代码：https://github.com/navganti/SIVO
29. FILD（临近图增量式闭环检测）
论文：Shan An, Guangfu Che, Fangru Zhou,Xianglong Liu, Xin Ma, Yu Chen.Fast and Incremental Loop Closure Detection usingProximity Graphs. pp. 378-385, The 2019 IEEE/RSJ International Conferenceon Intelligent Robots and Systems (IROS2019)
代码：https://github.com/AnshanTJU/FILD
30. object-detection-sptam（目标检测与双目 SLAM）
论文：Pire T, Corti J, Grinblat G. Online Object Detection and Localization on Stereo VisualSLAM System[J]. Journal of Intelligent & Robotic Systems, 2019:1-10.
代码：https://github.com/CIFASIS/object-detection-sptam
31. Map Slammer（单目深度估计 + SLAM）
论文：Torres-Camara J M, Escalona F, Gomez-DonosoF, et al. Map Slammer: Densifying Scattered KSLAM 3D Maps withEstimated Depth[C]//Iberian Robotics conference. Springer, Cham, 2019:563-574.
代码：https://github.com/jmtc7/mapSlammer
32. NOLBO（变分模型的概率 SLAM）
论文：Yu H, Lee B. Not Only LookBut Observe: Variational Observation Model of Scene-Level 3D Multi-ObjectUnderstanding for Probabilistic SLAM[J]. arXiv preprint arXiv:1907.09760, 2019.
代码：https://github.com/bogus2000/NOLBO
三、Multi-Landmarks / Object SLAM（12 项）
其实多路标的点、线、平面 SLAM 和物体
