Appendix

Study Resources

YouTube Lecture Series

Lecture Instructor Link
SLAM & Photogrammetry Cyrill Stachniss (Uni Bonn) YouTube Playlist
First Principles of Computer Vision Shree Nayar (Columbia) YouTube Channel
Multiple View Geometry Daniel Cremers (TU Munich) YouTube Playlist

Books

Book Author Key Topics
Introduction to Visual SLAM Xiang Gao et al. VO, optimization, Lie algebra, backend, loop closure — best entry-level SLAM book
Photogrammetric Computer Vision Wolfgang Förstner & Bernhard Wrobel Camera geometry, estimation, 3D reconstruction — mathematically rigorous
Multiple View Geometry in Computer Vision Richard Hartley & Andrew Zisserman Epipolar geometry, trifocal tensor, reconstruction — THE bible
Computer Vision: Algorithms and Applications Richard Szeliski Feature detection, stereo, motion, 3D — comprehensive reference (2nd ed. free PDF)
State Estimation for Robotics Timothy Barfoot Estimation theory, Lie groups, batch/recursive estimation — free PDF (2nd ed.)
Probabilistic Robotics Thrun, Burgard & Fox Bayes filters, EKF/particle-filter SLAM — the classical probabilistic foundation
Factor Graphs for Robot Perception Frank Dellaert & Michael Kaess Factor graphs, elimination, iSAM2 — the backend bible (free PDF)
SLAM Handbook Carlone, Kim, Barfoot, Cremers, Dellaert (eds.) From localization and mapping to spatial intelligence — free community book (2024-25)

Surveys

Survey Author/Year Key Concepts
Past, Present, and Future of SLAM Cadena 2016 The canonical orientation survey — robust perception age, open problems
Event-based Vision Survey Gallego 2020 Event cameras and algorithms (→ also in Level 10)

Code & Practice

Resource Link
SLAM Zero-to-Hero code exercises GitHub — Docker-based hands-on exercises for this roadmap's topics (feature detection, epipolar geometry, RANSAC, ICP, g2o/GTSAM/Ceres) and systems (ORB-SLAM2, Basalt, Kimera, FAST-LIO2, MASt3R-SLAM, ...); individual exercises are linked from the matching study notes
changh95/slam_lecture_codes GitHub — Full SLAM lecture code collection