mprib/caliscope

Multicamera Calibration for Motion Capture Workflows

What it solves

Caliscope simplifies the process of calibrating multicamera rigs used for 3D motion capture. It solves the difficulty of determining each camera's focal length, lens distortion, and its precise position and orientation relative to other cameras in a shared 3D space.

How it works

The toolkit uses calibration videos featuring targets like ChArUco boards, chessboards, or ArUco markers to estimate camera parameters. It can handle partial camera overlap by chaining links between cameras that share common views. It also supports double-sided targets for cameras facing each other. For those avoiding targets, an experimental markerless workflow allows calibration based on a person moving through the scene. Additionally, it uses ONNX-based models to estimate vertical orientation from video images alone.

Who it’s for

It is designed for researchers and developers working with 3D motion capture who need a reliable way to calibrate their camera arrays, whether through a GUI-based desktop app or a programmatic scripting API.

Highlights

  • Flexible Calibration: Supports ChArUco, chessboard, and ArUco markers, as well as markerless calibration.
  • Partial Overlap Support: Calibrates rigs even when not all cameras see the target simultaneously.
  • Rig Alignment: Ability to align the world origin to a calibration board or estimate vertical orientation from video.
  • Integration: Exports calibrations in TOML format, compatible with tools like Pose2Sim and anipose.
  • Quality Assurance: Includes a desktop app for visualizing processing stages and tracking landmarks with ONNX pose models to verify calibration quality.

Related

  • Project
    rameau-fr/MC-Calib

    A generic and robust calibration toolbox for multi-camera systems that supports both perspective and fisheye lenses in hybrid configurations.

  • Project
    koide3/direct_visual_lidar_calibration

    A target-less, automatic toolbox for LiDAR-camera extrinsic calibration that uses environment structure and texture for precise sensor alignment.

  • Project
    jiafeng5513/Evision

    A binocular vision system for camera calibration, disparity mapping, and 3D reconstruction using algorithms like ELAS and ADCensus.

  • Project
    cvg/GeoCalib

    GeoCalib is a Python library that estimates camera intrinsics and gravity direction from a single image using deep learning plus geometric optimisation. It supports several lens models, works with partial priors, can calibrate batches or multi‑camera rigs, and comes with training/evaluation code (OpenPano dataset) and demos. It outperforms prior single‑image calibration methods on standard benchmarks.

  • Project
    mikeferguson/robot_calibration

    A ROS2-based calibration toolkit for optimizing robot kinematic chains, sensor extrinsics, and mobile base parameters to ensure physical hardware matches the URDF model.