Welcome to the vailá Multimodal Toolbox ecosystem! 🤟🏾
This is not just another software suite; it's an idea. A revolutionary, open-source initiative that challenges the monopoly of commercial black-box software, providing free, versatile, and scientifically validated tools for biomechanical and human movement analysis.

The vailá Multimodal Toolbox encompasses two complementary open-source repositories designed to eliminate high licensing costs and proprietary barriers in motion capture and movement science:

vailá is a comprehensive multimodal analysis framework organized into three main operational sections:

• Frame A — File Manager: Unified file management sharing previewed operations between desktop GUI and CLI (Rename, Import, Export, Copy, Move, Remove, Directory Trees, Advanced Search, and SSH/remote file transfers).
• Frame B — Multimodal Analysis Pipelines:
  • Inertial Measurement Units (IMU): Accelerometer and gyroscope signal processing, orientation filtering, tilt and Euler angles.
  • Marker-based Motion Capture: Kinematic cluster marker analysis, rigid-body tracking, and full-body C3D processing (Vicon, Qualisys, OptiTrack).
  • Markerless 2D & 3D Computer Vision: MediaPipe Pose/FaceMesh/Hands, YOLOv26 Tracker/Pose/Segmentation/Training, SAM 3, Sapiens2 pose estimation, SAM3+DINOv3 3D reconstruction, and real-time Markerless Live camera streams.
  • Kinetic & Physiological Data: Multi-axis Force Plates (AMTI, Bertec, Center of Pressure, GRF), Instrumented Treadmill Load Cells, surface Electromyography (sEMG), GNSS/GPS trajectory tracking, MEG/EEG signal processing, and ECG/heart rate monitoring.
  • Standardized Biomechanical Protocols: Timed Up and Go (TUG 3D), Countermovement and Squat Jump analysis, Vector Coding for intersegmental coordination variability, Sit-to-Stand kinematics, Open Field animal tracking, and Soccer Field camera calibration (DLT2D/DLT3D).
• Frame C — Video Processing & Conversion Tools:
  • Video cutting, trimming, compression (H.264 / HEVC H.265 / H.266), multi-camera synchronization, pixel coordinate extraction, video distortion correction, and automated YouTube download pipelines.
  • 2D and 3D Direct Linear Transformation (DLT) calibration and 3D reconstruction pipelines.
  • Interactive C3D and CSV data inspection.

mkvis3d is an open-source, reproducible alternative to commercial suites such as C-Motion Visual3D and BTK Mokka:

• Interactive Local 3D Viewer: A zero-dependency HTML5 Canvas viewer running via a loopback local HTTP server in any modern browser. Supports real-time playback, orbit/pan/zoom, interactive distance measurements, marker-defined angle sidebar plots, multi-sequence Euler/Cardan angles, and synchronized analog channel charts.
• Native C3D Binary Parser: Complete NumPy-based binary reader supporting Intel, DEC VAX, and MIPS byte ordering, with both 16-bit signed integer and floating-point storage formats. Automatically normalizes POINT:UNITS to SI metres and matches reference oracles bit-for-bit.
• Mathematical Biomechanics Core:
  • Zero-lag Butterworth digital filtering (low-pass, high-pass, band-pass, band-stop).
  • Kabsch rigid-body registration for optimal rotation and translation estimation.
  • Grood & Suntay ISB joint coordinate systems (knee, hip, ankle joint kinematics).
  • Zeni et al. automated gait event detection (heel-strike and toe-off).
  • Dumas and de Leva body segment parameters (mass, center of mass, moments of inertia).
• Inverse Dynamics & Kinetics:
  • Full support for Force Plate types 1, 2, 3, 4, and 5, computing Center of Pressure (COP) and 3D Ground Reaction Force (GRF) vectors.
  • Recursive Newton-Euler equations of motion along the distal-to-proximal kinematic chain, calculating net 3D joint moments and joint powers.
  • Dynamic 3D GRF vector overlays rendered directly over force platforms in the 3D viewer.
• Open .vaila Project Format: A versioned ZIP/JSON specification encapsulating 3D point kinematics, analog signals, platform geometry, calculation history, and complete analysis provenance.
• Blender Integration: Dedicated Blender import add-on and automated script exporter for photorealistic scientific rendering.
• Standalone Distribution: Native single-file executables and double-clickable launchers for Linux, macOS (.command), and Windows (.bat).

flowchart LR
    subgraph VAILA["vailá — Multimodal Acquisition & Batch Engine"]
        F_A["Frame A<br/>File Manager"]
        F_B["Frame B<br/>Multimodal Pipelines<br/>(IMU, MoCap, Vision, EMG, Force)"]
        F_C["Frame C<br/>Video & DLT Reconstruction"]
    end

    subgraph FORMAT[".vaila Project Format & C3D / CSV"]
        V_DATA["Standardized 3D Kinematics<br/>+ Analog & Force Channels<br/>+ Analysis Provenance"]
    end

    subgraph MKVIS["mkvis3d — 3D Viewer & Biomechanics Core"]
        M_VIEW["Zero-Dependency<br/>Canvas 3D Viewer"]
        M_MATH["ISB Joint Kinematics<br/>Kabsch & Butterworth"]
        M_DYN["Inverse Dynamics<br/>Force Plates 1-5 & GRF"]
    end

    VAILA -->|".c3d / .csv / .vaila"| FORMAT
    FORMAT --> MKVIS
    MKVIS -.->|"Future native 3D module for Frame C"| VAILA

• Shared Mathematical Lineage: Algorithms validated in vailá production (such as filtering, calibrations, and landmark definitions) are integrated and cross-tested in mkvis3d.
• Interchangeable Data Formats: vailá captures, extracts, and exports motion data into C3D, CSV, and the open .vaila project format, which mkvis3d immediately ingests for high-speed 3D playback and recursive inverse dynamics.
• Unified Vision: Both tools operate under the GNU Affero General Public License v3.0 (AGPLv3), ensuring that scientific biomechanics software remains open, auditable, and unencumbered by restrictive licenses.

Find direct links to the specific help manuals, guides, and documentation for each repository below:

Single-command installers configure isolated virtual environments with pinned dependencies:

• Linux:

  wget -qO- https://raw.githubusercontent.com/vaila-multimodaltoolbox/vaila/main/install_vaila_linux.sh | bash

• macOS:

  /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/vaila-multimodaltoolbox/vaila/main/install_vaila_mac.sh)"

• Windows (PowerShell):

  [Net.ServicePointManager]::SecurityProtocol = [Net.ServicePointManager]::SecurityProtocol -bor 3072; irm https://raw.githubusercontent.com/vaila-multimodaltoolbox/vaila/main/install_vaila_win.ps1 | iex

Launch the interface from inside the vaila directory:

uv run vaila.py

Requires Python 3.12+ and uv:

git clone https://github.com/vaila-multimodaltoolbox/mkvis3d
cd mkvis3d
uv sync
uv run mkvis3d gui

Alternatively, launch the viewer using the OS-specific double-click launchers:

• 🐧 Linux: ./mkvis3d_launcher.sh
• 🍎 macOS: ./mkvis3d.command
• 🪟 Windows: mkvis3d.bat

In front of you stands a versatile and anarcho-integrated tool, designed to challenge the boundaries of commercial systems. This software, not a mere substitute, is a symbol of innovation and freedom, now available and accessible. We are determined to eliminate the barriers that protect the monopoly of expensive software, ensuring the dissemination of knowledge and accessibility. 🤟🏾🏴‍☠️🖥️

We have left the box open with vailá to insert your ideas and processing in a liberated manner. The only verdict is versatility; a vendetta against exorbitant costs, held as a vow, not in vain, for the value and veracity of which shall one day vindicate the vigilant and the virtuous in the field of motion analysis. Surely, this torrent of technology tends to be very innovative, so let me simply add that it is a great honor to have you with us, and you may call this tool vailá. 🤟🏾🏴‍☠️💡

"vailá" is an expression that blends the sound of the French word "voilà" with the direct encouragement in Portuguese "vai lá". It is a call to action, an invitation to initiative and freedom to explore, experiment, and create without the constraints imposed by expensive commercial software. "vailá" means "go there and do it!", encouraging everyone to harness the power of open science to perform analysis with data from multiple systems. 🤟🏾💻🎓⚔️

Junte-se a nós na libertação do software proprietário pago com a caixa de ferramentas vailá: Análise Versátil da Libertação Anarquista Integrada na Caixa de Ferramentas Multimodal.

Diante de você está uma ferramenta versátil, projetada para desafiar as fronteiras dos sistemas comerciais. Este software é um símbolo de inovação e liberdade, determinado a eliminar as barreiras que protegem o monopólio do software caro, garantindo a disseminação do conhecimento e a acessibilidade irrestrita.

Com o ecossistema vailá, você é convidado a explorar, experimentar e criar sem restrições. "vailá" significa "vai lá e faça!" — encorajando você a aproveitar seu poder para realizar análises biomecânicas com dados de múltiplos sistemas. 🤟🏾🏴‍☠️🇧🇷

If you utilize the vailá Multimodal Toolbox or mkvis3d in your scientific research, please cite our foundation papers:

@misc{vaila2024,
  title={vailá - Versatile Anarcho Integrated Liberation Ánalysis in Multimodal Toolbox},
  author={Paulo Roberto Pereira Santiago and Guilherme Manna Cesar and Ligia Yumi Mochida and Juan Aceros and others},
  year={2024},
  eprint={2410.07238},
  archivePrefix={arXiv},
  primaryClass={cs.HC},
  url={https://arxiv.org/abs/2410.07238}
}

@article{tahara2025predicting,
  title={Predicting walkway spatiotemporal parameters using a markerless, pixel-based machine learning approach},
  author={Tahara, Ariany K and Chinaglia, Abel G and Monteiro, Rafael LM and Bedo, Bruno LS and Cesar, Guilherme M and Santiago, Paulo RP},
  journal={Brazilian Journal of Motor Behavior},
  volume={19},
  number={1},
  pages={e462--e462},
  year={2025}
}

@article{Mochida2025,
  author={Mochida, Ligia Yumi and Santiago, Paulo R. P. and Lamb, Miranda and Cesar, Guilherme M.},
  title={Multimodal Motion Capture Toolbox for Enhanced Analysis of Intersegmental Coordination in Children with Cerebral Palsy and Typically Developing},
  journal={Journal of Visualized Experiments},
  year={2025},
  number={206},
  pages={e69604},
  doi={10.3791/69604},
  url={https://www.jove.com/t/69604/multimodal-motion-capture-toolbox-for-enhanced-analysis}
}

@article{chinaglia2026automating,
  title={Automating Timed Up and Go Phase Segmentation and Gait Analysis via the tugturn Markerless 3D Pipeline},
  author={Chinaglia, Abel Gon{\c{c}}alves and Cesar, Guilherme Manna and Santiago, Paulo Roberto Pereira},
  journal={arXiv preprint arXiv:2602.21425},
  year={2026},
  doi={10.48550/arXiv.2602.21425},
  url={https://arxiv.org/abs/2602.21425}
}

Contributions are warmly welcomed across the entire ecosystem!

• To contribute to the acquisition and batch processing pipelines, see the vailá Contributing Guide.
• To contribute to 3D visualization, C3D parsers, or inverse dynamics math, see the mkvis3d Contribution Guide.

Feel free to fork the repositories, submit issues, and propose pull requests. Be bold and experiment! ⚔️

Both projects in this ecosystem are licensed under the GNU Affero General Public License v3.0 (AGPLv3).
This license ensures that any use of the software, including network or cloud service usage, preserves freedom and mandates complete source code availability.

See the LICENSE file or visit https://www.gnu.org/licenses/agpl-3.0.html for details.