# ethz-asl/okvis

OKVIS: Open Keyframe-based Visual-Inertial SLAM.

Repository: https://github.com/ethz-asl/okvis
Canonical: https://ross.abutalabs.com/products/okvis
Language: C++
License: NOASSERTION
License Family: other
Last push: 2021-08-24T10:19:14+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": 3863, "days_push": 1835, "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 1366, forks 541 (observed 2026-08-28T04:04:31.361128+00:00)

## What it is
OKVIS is a C++ implementation of keyframe-based visual-inertial SLAM/odometry using nonlinear optimization, from ETH Zurich research. It provides a library plus demo application for estimating camera/IMU trajectory from synchronized image and inertial data.

## Use cases
- run visual-inertial odometry on camera and IMU data
- estimate trajectories for drones or robots with a VI sensor
- reproduce keyframe-based visual-inertial SLAM research results
- integrate SLAM into a C++ robotics project
- process datasets from a Skybotix VI sensor

## When to choose
- you need proven visual-inertial odometry with nonlinear optimization
- you work with ROS/Eigen-based robotics stacks and C++
- you want the reference implementation of the OKVIS papers

## When to avoid
- you need actively maintained software with recent fixes
- you want a plug-and-play SLAM solution rather than a research codebase
- you need support for modern OpenCV versions or non-Linux platforms out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, simulation, math, parser
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp
- tags: slam, visual-inertial-odometry, keyframe, nonlinear-optimization, research-software, cmake, algorithms, linux, ros

## Member repositories
- ethz-asl/okvis (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.361128+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 2026-08-30T04:41:12.281502+00:00, confidence not recorded.
  - readme: https://github.com/ethz-asl/okvis (fetched 2026-08-28T04:04:31.361128+00:00, sha 55bf7246fade)
- Data as of 2026-08-30T08:39:29.467469+00:00.