# tzutalin/awesome-visual-slam

:books: The list of vision-based SLAM / Visual Odometry open source, blogs, and papers

Repository: https://github.com/tzutalin/awesome-visual-slam
Canonical: https://ross.abutalabs.com/products/awesome-visual-slam
License Family: other
Topics: slam, ros, computervision, reconstruction, point-cloud, learning, books
Last push: 2022-05-10T17:57:19+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3705, "days_push": 1576, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2429, forks 438 (observed 2026-08-28T04:06:50.984166+00:00)

## What it is
A curated awesome-list collecting open-source vision-based SLAM and Visual Odometry resources, including libraries (OpenCV, g2o, ceres-solver, OctoMap), benchmark datasets (KITTI, TUM, nuScenes, Waymo), evaluation tools, and projects like PTAM and Kimera. It is a reference index of links, not a software package itself.

## Use cases
- find open source visual SLAM libraries
- best visual odometry projects on github
- datasets to benchmark SLAM odometry algorithms
- learn visual SLAM from scratch resources
- loop closure detection libraries
- graph optimization solvers for SLAM
- RGBD monocular SLAM open source implementations

## When to choose
- You want a single curated starting point for discovering SLAM libraries, datasets, tools, and papers
- You are comparing visual odometry or SLAM implementations before committing to one
- You need pointers to benchmark datasets like KITTI, TUM RGB-D, or Waymo for trajectory evaluation

## When to avoid
- You need a working SLAM algorithm you can compile and run - this is a list of links, not software
- You need maintained, licensed code with support - individual linked projects vary in quality and upkeep
- You need lidar-based or non-visual SLAM resources - the list focuses on vision-based approaches

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: documentation
- domain: computer-vision, robotics, autonomous-vehicles, awesome-lists
- platform: cpp, cross-platform
- tags: awesome-list, slam, visual-slam, visual-odometry, ros, point-cloud, 3d-reconstruction, loop-closure, graph-optimization, benchmark-datasets, mapping, localization, curated-resources, papers

## Member repositories
- tzutalin/awesome-visual-slam (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.984166+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:31:32.377444+00:00, confidence not recorded.
  - readme: https://github.com/tzutalin/awesome-visual-slam (fetched 2026-08-28T04:06:50.984166+00:00, sha dc3cafcd73d7)
- Data as of 2026-08-30T08:39:29.467469+00:00.