NOTE: the docs below align with main and not necessarily PyPI

I will be pushing a minor update to PyPI in the coming days [now March 16, 2026].

Caliscope

Multicamera Calibration for Motion Capture Workflows

Caliscope is a permissively licensed multicamera calibration tool. Bundle adjustment across 3+ cameras requires a good initial estimate of camera positions to converge quickly and reliably. Caliscope is designed to produce that good initial estimate and rapidly solve for a quality calibration.

Demo

5_cam_demo_small.mp4

Quick Start

# Desktop app (GUI + 3D visualization)
uv pip install caliscope[gui]

# Library only (scripting, CI, servers — no GUI dependencies)
uv pip install caliscope

Full installation instructions are in the docs.

For a walkthrough with test data after installing, see the sample project.

---

Features

Feature	What it does
Pairwise PnP initialization	Estimates camera positions from stereopairs chained transitively, so bundle adjustment starts from a reliable point
Flexible calibration targets	ChArUco, ArUco, and chessboard targets; a single ArUco marker on a sheet of paper can calibrate a wide volume
Mirror board support	A charuco board printed on both sides of a rigid surface links cameras that never share a common view
Visual feedback	Inspect distortion models, 3D camera positions, reprojection errors, and world scale accuracy at each stage
Outlier filtering	Filter calibration points by reprojection error after optimization and re-solve
Aniposelib export	Automatically generates camera_array_aniposelib.toml for use with aniposelib-compatible tools

Tracking and Reconstruction

Caliscope includes a basic reconstruction pipeline for verifying calibration quality. You can load ONNX pose estimation models (RTMPose, SLEAP, DeepLabCut, or custom) and export 3D trajectories in CSV and TRC (OpenSim) formats. For more complete reconstruction workflows, tools like anipose and Pose2Sim will serve you better. The aniposelib-compatible export makes it straightforward to use Caliscope for calibration and hand off to these tools for downstream processing.

Scripting API

The standard install (uv pip install caliscope) exposes intrinsic and extrinsic camera calibration as importable Python functions. Rich progress bars appear automatically; pass progress=None for silent operation.

For the desktop app with 3D visualization: uv pip install caliscope[gui]

See the Scripting API docs and scripts/demo_api.py for examples.

Community & Support

To report a bug or request a feature, please open an issue. For questions, post in Discussions.

Acknowledgments

Caliscope was inspired by anipose, created by Lili Karashchuk, PhD, which demonstrated the value of accessible multicamera calibration for the research community.

License

Caliscope is licensed under the BSD 2-Clause license.