# JakobEngel/dso

Direct Sparse Odometry

Repository: https://github.com/JakobEngel/dso
Canonical: https://ross.abutalabs.com/products/dso
Language: C++
License: GPL-3.0
License Family: copyleft
Last push: 2024-02-23T16:15:26+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3584, "days_push": 922, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2454, forks 920 (observed 2026-08-28T04:06:53.120164+00:00)

## What it is
DSO (Direct Sparse Odometry) is a C++ library implementing monocular visual odometry using direct sparse methods with photometric calibration. It estimates camera trajectory and a sparse 3D map from image sequences, and ships with a binary for running on benchmark datasets.

## Use cases
- estimate camera trajectory from monocular video
- run visual odometry on the TUM monoVO dataset
- build SLAM or AR applications needing camera pose tracking
- research direct-method odometry and photometric calibration
- recover sparse 3D point clouds from image sequences
- run odometry on embedded ARM devices

## When to choose
- you need monocular visual odometry with photometric calibration
- you want a well-cited research implementation of direct sparse methods
- you need a C++ library to link into a larger robotics or AR project
- you are benchmarking odometry on the TUM monoVO dataset

## When to avoid
- you need RGB-D or stereo odometry out of the box
- you want a maintained production SLAM system with active support
- you need loop closure or full SLAM rather than pure odometry
- you require a permissive license (it is GPL-3.0)

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, graphics, math
- domain: computer-vision, robotics, autonomous-vehicles
- platform: cpp, cross-platform
- tags: visual-odometry, slam, direct-methods, monocular-camera, photometric-calibration, research-code, algorithms, linux

## Member repositories
- JakobEngel/dso (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:53.120164+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 2026-08-30T02:30:07.022682+00:00, confidence not recorded.
  - readme: https://github.com/JakobEngel/dso (fetched 2026-08-28T04:06:53.120164+00:00, sha 264413a45021)
- Data as of 2026-08-30T08:39:29.467469+00:00.