JakobEngel/dso

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2454 stars · 920 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

computer-vision graphics math computer-vision robotics autonomous-vehicles cpp cross-platform visual-odometry slam direct-methods monocular-camera photometric-calibration research-code algorithms linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="JakobEngel/dso")