Repolode
Submit
MaxLiu22

MaxLiu22/Motion2MixamoRig

Retargets human motion from a video or still photo onto an Adobe Mixamo-rigged 3D character, exporting a skinned .glb file.

View on GitHub
Stars
1,374
Forks
173
Open issues
10
Last commit
3 days ago

What is it?

Motion2MixamoRig takes the motion of a single person in a video, or the pose in a still photo, and applies it to a character rigged for Adobe Mixamo. The output is a skinned character file (.glb) that can be imported into Blender or Unity, along with preview videos or images of the skeleton, character, and a side-by-side comparison.

The project is a Python command-line pipeline (`m2mr`) that runs human pose extraction, retargets the rotations to the Mixamo skeleton, and renders previews. Reusing a saved skeleton with `--skeleton` lets you apply the same motion to a different character without repeating the slow extraction step. It also ships a Blender 4.2+ extension that runs the same pipeline in an external Python environment, so users can work without coding.

The SMPL-X body model and Mixamo character FBX must be downloaded separately because of their own licenses. Inference weights are fetched automatically on the first run, about 5 GB. ffmpeg is recommended so that output videos include audio tracks and play in browsers.

Key features

  • 01Extracts a single person's motion from video or a still photo.
  • 02Retargets the motion onto Mixamo-rigged characters, including FBX models re-exported from Cinema 4D.
  • 03Exports a skinned .glb character plus skeleton motion data.
  • 04Reuses saved skeletons to apply one motion to several characters quickly.
  • 05Provides a Blender 4.2+ extension that runs the pipeline without coding.

Use cases

  • Giving game characters motion captured from reference videos.
  • Producing animation previews for Mixamo characters in Blender or Unity.
  • Turning a single pose photo into a static 3D pose on a rigged character.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/MaxLiu22/Motion2MixamoRig.git
  2. 2

    Create a virtualenv and install dependencies

    python -m venv .venv && source .venv/bin/activate && pip install --upgrade pip setuptools wheel && pip install "numpy>=1.26" && pip install --no-build-isolation "chumpy==0.70" && pip install -e .
  3. 3

    Check assets and environment

    m2mr doctor
  4. 4

    Run the pipeline on the latest video in assets/video/

    m2mr run

Things to know

  • Experimental project; the README says it is currently experimental.
  • Requires you to manually download an SMPL-X model (registration required, non-commercial by default) and a Mixamo character.
  • First run downloads about 5 GB of inference weights, and CPU extraction is slow.
  • Only supports single-person clips with the whole body in frame.

Topics

#motion-capture#3d-animation#pose-estimation#mixamo#blender#retargeting#game-development

FAQ

What is Motion2MixamoRig?
Retargets human motion from a video or still photo onto an Adobe Mixamo-rigged 3D character, exporting a skinned .glb file. Motion2MixamoRig takes the motion of a single person in a video, or the pose in a still photo, and applies it to a character rigged for Adobe Mixamo. The output is a skinned character file (.glb) that can be imported into Blender or Unity, along with preview videos or images of the skeleton, character, and a side-by-side comparison.
Is Motion2MixamoRig free to use? What license does it have?
Motion2MixamoRig is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is Motion2MixamoRig still maintained?
Actively maintained. The last commit to Motion2MixamoRig was on Oct 17, 2026.
What can I use Motion2MixamoRig for?
Giving game characters motion captured from reference videos. Producing animation previews for Mixamo characters in Blender or Unity. Turning a single pose photo into a static 3D pose on a rigged character.
How do I install Motion2MixamoRig?
Clone the repository: git clone https://github.com/MaxLiu22/Motion2MixamoRig.git Create a virtualenv and install dependencies: python -m venv .venv && source .venv/bin/activate && pip install --upgrade pip setuptools wheel && pip install "numpy>=1.26" && pip install --no-build-isolation "chumpy==0.70" && pip install -e . Check assets and environment: m2mr doctor Run the pipeline on the latest video in assets/video/: m2mr run
Where can I get Motion2MixamoRig?
The source code and installation instructions are on GitHub: https://github.com/MaxLiu22/Motion2MixamoRig

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects