Personal page of SLAM Resources to follow up current SLAM trends and papers.

Inspired by Event-based vision resources

Also reference pages are listed on Pages collect resources for SLAM

What I cannot create, I do not understand. - richard feynman

Do the simplest thing that could possibly work

• Algorithms
• Sensor Model
• Datasets and Simulators
• Calibration
• Evaluation
• Workshops&Tutorials
• Survey
• Papers
• Deep Learning Related SLAM
• Semantic SLAM - Object level SLAM
• Books
• Pages : collect resources for SLAM
• Toolkit
• Videos, Lectures
• Visualization

• Homography

• Fundemental

• SFM

• Visual-Inertial Alignment

• Data Association : How to Define Data Selection, Match, Define Error

  • Direct Dense

  • Direct Sparse

  • Feature (Sparse)

    • Corner Selection

    • Descriptors

  • Feature Match

• Motion Prior

  • Constant Velocity Model

  • Decaying Velocity Model

  • IMU Propagation

  • Using Prev Pose

• Pose Estimation : How to minimize Error

  • PnP : Perspective N Points

  • Motion Only BA : Coarse-Fine

  • Local BA : Coarse-Fine

    • Sliding Window : Continous N Frame window

    • Topological : Releated Keyframes

• Map Type

• Map Generation

• Relocalization

• Pose Graph Optimization : Loop Closure

• Place Recognition

• Factor Graph

• Image_Undistorter
• Camera Models - modified version of CamOdoCal
• ROS Image Proc => Wiki Documentation of ROS image pipeline

• Noise Model

• IMU Propagation

• IMU Preintegration

• GML: C++ Calibration Toolbox
• ROS camera calibration
• Camera Calibration Toolbox for Matlab
• CamOdoCal
• OCamCalib: Omni-Camera Calibration

• TUM, Online Photometric calibration

• Kalibr
• Vicalib
• Inervis Toolbox-Matlab

• IMUSensorModels-Data_Analysis_Tools
• Kalibr_allan
• NaveGO: an open-source MATLAB/GNU Octave toolbox for processing INS and performing IMU analysis
• imu_utils : ROS package tool to analyze the IMU performance

• Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
• Keyframe-based monocular SLAM: design, survey, and future directions
• Local Invariant Feature Detectors: A Survey
• Visual Odometry Part I: The First 30 Years and Fundamentals
• Visual odometry: Part II: Matching, robustness, optimization, and applications
• Visual simultaneous localization and mapping : a survey
• Simultaneous Localization and mapping : a survey of current trends in Autonomous Driving
• Visual SLAM Algorithms : a survey from 2010 to 2016

• Visual Odometry, Nister, CVPR 04
• Scalable monocular SLAM, E. Eade,T. Drummond, CVPR 06
• Parallel Tracking and Mapping(PTAM) for Small AR Workspaces, Georg Klein, David Murray, ISMAR 07
• MonoSLAM, AJ Davison, Reid, Molton, Stasse, PAMI 07
• Accurate Quadrifocal Tracking for Robust 3D Visual Odometry, IEEE RA-L 07, A.I. Comport, E. Malis and P. Rives
• DTAM: Dense Tracking and Mapping in Real-Time, RA Newcombe, Steven J. Lovegrove, AJ Davison, ICCV 11
• Dense Visual SLAM for RGB-D Camera
• Semi-Dense Visual Odometry, J. Engel, J. Sturm, AJ Davision, ICCV 13
• SVO: Fast Semi-Direct Monocular Visual Odometry, C Forster, M. Pizzoli, D. Scarammuzza, ICRA 14
• LSD-SLAM: Large-Scale Direct Monocular SLAM, J. Engel, T.Schoeps, AJ Davision, ECCV 14
• REMODE, M. Pizzoli, C. Forster, D. Scrammuza, ICRA 14
• Dense Visual-Inertial Odometry for Tracking of Aggressive Motions
• ORB_SLAM, R. Mur-Artal, J. Montiel, JD Tardós, IEEE TRO 15
• OKVIS, S. Leutenegger, S. Lynen, M. Bosse, R. Siegwart, P.Furgale, IJRR 15
• DPPTAM, Concha, Alejo and Civera, Javier, IROS 15
• SOFT2 : Stereo odometry based on careful feature selection and tracking, I Cvišić, I Petrović, ECCV 15
• EVO: A Geometric Approach to Event-Based 6-DOF Parallal Tracking and Mapping in Real-time, H. Rebecq, T. Horstschaefer, G. Gallego, D. Scaramuzza, IEEE RA-L 16
• On-Manifold Preintegration for Real-Time VIO, C. Forster, L. Carlone, F. Dellaert, D. Scaramuzza, IEEE RA-L 17
• ORB_SLAM2, R Mur-Artal, JD Tardós, IEEE TRO 17
• Direct Sparse Odometry, J. Engel, V. Kltun, AJ Davison, PAMI 17
• Real-time VIO for Event Cameras using Keyframe-based Nonlinear Optimization, H.Rebecq, T. Horstschaefer, D. Scaramuzza, BMVC 17
• ElasticFusion: Dense SLAM Without A Pose Graph
• Dense RGB-D-Inertial SLAM with Map Deformations
• SVO for Monocular and Multi-Camera Systems, C. Forster, Z. Zhang, M. Gassner, M. Werlberger, D. Scaramuzza, IEEE TRO 17
• VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator, T. Qin, Tong and Li, Peiliang, Shen, Shaojie, IEEE TRO 18
• Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios, T. Rosinol Vidal, H.Rebecq, T. Horstschaefer, D. Scaramuzza, IEEE RA-L 18
• Event-based, 6-DOF Camera Tracking from Photometric Depth Maps, Gallego, Jon E. A. Lund, E. Mueggler, H.Rebecq, T. Delbruck, D. Scaramuzza, PAMI 18
• [Loosely-Coupled Semi-Direct Monocular SLAM, Seong Hun Lee and Javier Civera, IEEE Robotics and Automation Letters] (https://arxiv.org/pdf/1807.10073.pdf)

• DeepVO: A Deep Learning approach for Monocular Visual Odometry, Vikram Mohanty, Shubh Agrawal, Shaswat Datta, Arna Ghosh, Vishnu D. Sharma, Debashish Chakravarty
• CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction, CVPR, 2017, Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab
• Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry, Nan Yang, Rui Wang, J¨org St¨uckler, Daniel Cremers
• UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning
• SfMLearner++: Learning Monocular Depth & Ego-Motion using Meaningful Geometric Constraints, Vignesh Prasad, Brojeshwar Bhowmick
• CNN-SVO: Improving the Mapping in Semi-Direct Visual OdometryUsing Single-Image Depth Prediction, Shing Yan Loo, Ali Jahan, Amiri, Syamsiah Mashohor, Sai Hong Tang and Hong Zhang1
• Learning monocular visual odometry with dense 3D mapping from dense 3D flow, Cheng Zhao, Li Sun, Pulak Purkait, Tom Duckett and Rustam Stolkin1
• Learning to Prevent Monocular SLAM Failure using Reinforcement Learning, Vignesh Prasad, Karmesh Yadav, Rohitashva Singh Saurabh, Swapnil Daga, Nahas Pareekutty, K. Madhava Krishna. Balaraman Ravindran, Brojeshwar Bhowmick
• CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM, Michael Bloesch, Jan Czarnowski, Ronald Clark, Stefan Leutenegger, Andrew J. Davison.
• LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo. ECCV, 2018, Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J. Davison.
• DeepTAM: Deep Tracking and Mapping, Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
• Deep Auxiliary Learning for Visual Localization and Odometry, Abhinav Valada, Noha Radwan, Wolfram Burgard
• Mask-SLAM: Robust feature-based monocular SLAM by masking using semantic segmentation, CVPR 2018, Masaya Kaneko Kazuya Iwami Toru Ogawa Toshihiko Yamasaki Kiyoharu Aiza
• MagicVO: End-to-End Monocular Visual Odometry through Deep Bi-directional Recurrent Convolutional Neural Network, Jian Jiao, Jichao Jiao, Yaokai Mo, Weilun Liu, Zhongliang Deng
• Global Pose Estimation with an Attention-based Recurrent Network
• Geometric Consistency for Self-Supervised End-to-End Visual Odometry, CVPR 2018, Ganesh Iyer, J. Krishna Murthy, Gunshi Gupta1, K. Madhava Krishna1, Liam Paull
• DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction, CVPR 2018, Arun CS Kumar Suchendra M. Bhandarkar, Mukta Prasad
• DeepFusion: Real-Time Dense 3D Reconstruction for Monocular SLAM using Single-View Depth and Gradient Predictions. ICRA, 2019, Tristan Laidlow, Jan Czarnowski, Stefan Leutenegger.
• KO-Fusion: Dense Visual SLAM with Tightly-Coupled Kinematic and Odometric Tracking. ICRA, 2019, Charlie Houseago, Michael Bloesch, Stefan Leutenegger.
• DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features, Rong Kang, Xueming Li, Yang Liu, Xiao Liu, Jieqi Shi

• Probabilistic Data Association for Semantic SLAM, Sean L. Bowman Nikolay Atanasov Kostas Daniilidis George J. Pappas
• Fusion++: Volumetric Object-Level SLAM. 3DV, 2018, John McCormac, Ronald Clark, Michael Bloesch, Stefan Leutenegger, Andrew J. Davison.
• DynSLAM: Simultaneous Localization and Mapping in Dynamic Environments,Ioan Andrei Brsan and Peidong Liu and Marc Pollefeys and Andreas Geiger

• Python package for evaluation of odometry and SLAM
• uzh-rpg : rpg_trajectory_evaluation, papers
• TUM, useful tools for the RGBD benchmark
• TUM, Matlab tools for evaluation, provided by TUM, DSO : Direct Sparse Odometry

• Awesome SLAM Dataset :
  • 2018 TUM Visual Inertial Dataset : Stereo,IMU,Calibrated(+Photometric)
  • 2018 MVSEC : Multi Vehicle Stereo Event Dataset : Stereo, Event, IMU
  • 2016 TUM Mono Dataset : Mono,IMU,Photometric Calibration
  • 2016 RPG Event Dataset : Mono,Event,IMU
  • 2016 EuRoC Dataset : Stereo,IMU
  • 2015 TUM Omni Dataset : Mono,Omni,IMU
  • 2014 ICL-NUIM Dataset : Mono,RGB-D
  • 2014 MRPT-MALAGA Dataset
  • 2013 KITTI Dataset

• 2014 CVPR Workshop and Tutorials
• 2015 ICCV Imperial college Workshop
• 2016 ICRA SLAM Tutorials
• 2017 CVPR Tutorials - pages removed
• 2018 ECCV Visual Localization Workshop
• 2018 ECCV Workshop
• 2018 IROS Workshop - Unconventional Sensing and Processing for Robotic Visual Perception, No Material..
• 2018 ECCV 3D Reconstruction meets Semantics
• 2018 CVPR Tutorials - First Deep SLAM Workshop
• 2018: http://cvpr2018.thecvf.com/program/tutorials
• 2017: http://cvpr2017.thecvf.com/program/tutorials
• 2016: http://cvpr2016.thecvf.com/program/tutorials
• 2015: http://www.pamitc.org/cvpr15/tutorials.php
• 2014: http://www.pamitc.org/cvpr14/tutorials.php
• 2013: http://www.pamitc.org/cvpr13/tutorials.php

• slambook-no en,kr translation, source

• awesome-SLAM-list
• SFM-Visual-SLAM
• Event Vision Realted Resources - ETH Zurich

• OpenCV-Computer Vision
• MexOpenCV-Matlab mex functions for OpenCV

• Eigen-Linear Algebra
• Sophus-Lie Groups using Eigen

• Ceres-NLLS Solver library
• g2o: A General Framework for Graph Optimization

• Open3D
• Point Cloud Library

• Multiple View Geometry, TUM, 2014
• Roboot Mapping, University Freiburg, 2013

• ARKit: Understanding ARKit Tracking and Dtection