mapillary/OpenSfM

Open source Structure-from-Motion pipeline

What it solves

OpenSfM provides a way to reconstruct 3D scenes and determine the exact positions and angles of cameras (poses) using a set of multiple images. It simplifies the process of turning 2D photographs into 3D spatial data.

How it works

The library functions as a processing pipeline that uses basic Structure from Motion (SfM) modules for feature detection and matching, as well as minimal solvers. To increase accuracy and geographical alignment, it can integrate data from external sensors like GPS and accelerometers.

Who it’s for

It is designed for developers and researchers working on 3D reconstruction, computer vision, and spatial mapping.

Highlights

  • Robust and scalable reconstruction pipeline.
  • Integration of GPS and accelerometer data for geographical alignment.
  • Includes a JavaScript viewer for debugging the pipeline and previewing 3D models.

Related

  • Project
    borglab/gtsfm

    GTSfM is a modular, parallelized end-to-end Structure-from-Motion pipeline that reconstructs 3D scenes from images using distributed computing.

  • Project
    colmap/colmap

    COLMAP is an open‑source Structure‑from‑Motion and Multi‑View Stereo pipeline that automatically turns collections of photos into 3‑D models. It offers a GUI, command‑line tools, Python bindings, GPU‑accelerated feature extraction, and cross‑platform binaries, making it a go‑to foundation for research and applications in computer vision, robotics, AR/VR, and any workflow that needs camera poses and dense scene geometry.

  • Project
    cvg/vidmap

    VidMap is an offline Structure-from-Motion system that reconstructs 3D maps and camera trajectories from video by exploiting temporal data and global optimization.

  • Project
    cre185/InstantSfM

    A GPU-native Structure from Motion (SfM) pipeline that accelerates the process of reconstructing 3D structures from 2D images, including integrated support for 3D Gaussian Splatting.

  • Project
    dkogan/mrcal

    mrcal is a generic toolkit for solving camera calibration and Structure-from-Motion problems, providing C and Python libraries and command-line tools.