# uzh-rpg/rpg_svo

Semi-direct Visual Odometry

Repository: https://github.com/uzh-rpg/rpg_svo
Canonical: https://ross.abutalabs.com/products/rpg_svo
Language: C++
License: GPL-3.0
License Family: copyleft
Last push: 2019-08-22T21:27:36+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": 4557, "days_push": 2568, "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 2229, forks 870 (observed 2026-08-28T04:06:28.943481+00:00)

## What it is
SVO is a semi-direct monocular visual odometry pipeline written in C++ that estimates camera motion from image sequences. It is research code from the University of Zurich Robotics and Perception Group, released under GPLv3 with a commercial edition available.

## Use cases
- estimate camera trajectory from monocular video
- visual odometry for drone navigation
- track camera pose in real time on a robot
- benchmark SLAM/odometry algorithms
- build state estimation for micro aerial vehicles

## When to choose
- you need fast, lightweight monocular visual odometry on Linux with ROS
- you are doing robotics research on state estimation and want a citable baseline
- you work with micro aerial vehicles and limited compute

## When to avoid
- you need actively maintained software - the last release was 2019 and it targets old ROS/Ubuntu versions
- you need stereo, RGB-D, or full SLAM with loop closure
- you need a permissively licensed library for a commercial product without contacting the authors

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, robotics, image-processing
- domain: robotics, computer-vision, autonomous-vehicles
- platform: cpp
- tags: visual-odometry, slam, monocular-camera, semi-direct, ros, research-code, linux

## Member repositories
- uzh-rpg/rpg_svo (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:28.943481+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 2026-08-30T02:44:41.126708+00:00, confidence not recorded.
  - readme: https://github.com/uzh-rpg/rpg_svo (fetched 2026-08-28T04:06:28.943481+00:00, sha 215524a2e76f)
- Data as of 2026-08-30T08:39:29.467469+00:00.