# mapillary/OpenSfM

Open source Structure-from-Motion pipeline

Repository: https://github.com/mapillary/OpenSfM
Canonical: https://ross.abutalabs.com/products/opensfm
Homepage: https://www.opensfm.org/
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: opencv, python, sfm, 3d-reconstruction
Last push: 2026-08-25T22:56:54+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 8, longevity 100
- inputs: {"age_days": 4312, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3795, forks 901 (observed 2026-08-28T04:08:19.906776+00:00)

## What it is
OpenSfM is a Python Structure-from-Motion library that reconstructs camera poses and 3D scenes from multiple images, including feature detection/matching, minimal solvers, and GPS/IMU integration for geospatial alignment. This mapillary repository is no longer under active development and has moved to the OpenSfM/OpenSfM repository.

## Use cases
- reconstruct 3d scenes from photo collections
- estimate camera poses from multiple images
- build a photogrammetry pipeline in python
- align 3d reconstructions with gps data
- run structure from motion on drone imagery

## When to choose
- you need a python-based SfM pipeline with sensor fusion for geolocation
- you want a BSD-licensed library you can extend for 3d reconstruction research

## When to avoid
- you want active development - use the successor OpenSfM/OpenSfM repository instead
- you need a polished end-user photogrammetry application rather than a library

## Facets
- artifact type: library
- maturity: abandoned
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, photography
- platform: python
- tags: structure-from-motion, 3d-reconstruction, photogrammetry, opencv, camera-pose-estimation, feature-matching, deprecated-repo, algorithms, linux, macos, docker

## Member repositories
- mapillary/OpenSfM (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:19.906776+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 2026-08-29T18:26:57.005541+00:00, confidence not recorded.
  - readme: https://github.com/mapillary/OpenSfM (fetched 2026-08-28T04:08:19.906776+00:00, sha 401fd607b0ee)
  - homepage: https://www.opensfm.org/ (fetched 2026-08-29T09:21:59.841300+00:00, sha 285275b4bba1)
- Data as of 2026-08-30T08:39:29.467469+00:00.