MoCap AI — Video-to-Armature Motion Capture for Blender

MediaPipe-powered body, face and hand tracking with retargeting. 100% local on your machine. No cloud, no marker suit, no network — just a video and a click.

---

Why MoCap AI

Traditional mocap needs a suit, a stage, and a five-figure budget. AI pose estimation runs on ordinary phone or webcam footage and is good enough for indie game characters, virtual influencers, and animatic blocking. MoCap AI plumbs it into Blender's animation system with proper retargeting so the output drops onto your existing rig. Everything runs on your own computer with Google MediaPipe — your footage never leaves the machine.

---

Features

• Local MediaPipe capture (modern Tasks interface) — body, face shape keys, hand bones, or full body; landmark models are bundled, so it runs fully offline
• Frame range and step controls for partial captures; keyframes honour your Start Frame and Frame Step
• Model Accuracy (Fast, Balanced, Accurate) and Detection Confidence — real MediaPipe options in Preferences
• Smoothing — Gaussian filter on bone curves (None, Low, Medium, High)
• Retargeting to Rigify, Auto-Rig Pro, Mixamo, or custom humanoid rigs
• Foot-sliding fix when ground contact frames are detected
• Batch processing — queue several videos, each becomes its own action
• Per-capture frame cache, cleared before every run and clearable on demand
• Wait-cursor and progress feedback during long captures

---

Compatibility

• Blender: 4.2 LTS through 5.1 (developed and tested on 5.2)
• OS: Windows, macOS, Linux
• Dependencies: the free MediaPipe and OpenCV Python packages, installed into Blender's own Python (both run entirely on-device). The landmark models ship inside the add-on, so there is no separate model download. The add-on detects the packages and tells you exactly what to install if either is missing.

---

What you get

• MoCap AI add-on (pure Python, no compiled binaries)
• README with full quick-start and per-OS dependency install guide
• Free updates for the 1.x series
• Support through marketplace messaging

---

Limitations

• Pose estimation runs on the main thread; long videos block the UI (the wait cursor and status text keep you informed).
• Retargeting works best for humanoid rigs whose proportions match the source.
• Neck, head and foot bones follow the matching MediaPipe landmarks (nose, ears, ankles, toes); their accuracy depends on those being visible in the footage.

---

Install

Open Edit, then Preferences, then Add-ons, then Install from Disk. Pick the MoCap AI add-on ZIP and enable it. Install the two free Python packages into Blender's own Python (step-by-step, per-OS instructions are in the included README). The landmark models are already inside the ZIP, so there is nothing else to download. Press the N key in the 3D Viewport to open the MoCap AI tab.

---

Changelog — version 1.1.0

• Migrated capture to the modern MediaPipe Tasks interface, so it runs on the current MediaPipe releases that install on today's Blender (the older interface it previously relied on was removed upstream).
• Bundled the official pose, hand and face landmark models inside the add-on — capture is fully offline with no separate model download.
• Now a 100% local pipeline. Removed the OpenPose backend and the remote upload path entirely — no video frames ever leave your machine and there are no network calls anywhere.
• Added full per-OS dependency install instructions and in-app detection with a clear plain-English message when MediaPipe or OpenCV is missing.
• Fixed frame extraction so the pipeline always reads back exactly the frames it wrote.
• Each capture uses a fresh frame cache, so stale frames from an earlier video can never be re-used. Added a Clear Frame Cache button.
• Keyframes now honour Start Frame and Frame Step.
• The generated armature no longer contains unanimated bones — neck, head and feet are now driven from MediaPipe landmarks.
• Replaced the non-functional Model Path and Enable GPU settings with real MediaPipe options (Model Accuracy and Detection Confidence).
• Compatibility now correctly stated as Blender 4.2 through 5.1, including the new action system in 4.4 and later.

---

License

GPL-3.0. Standard for Blender add-ons.

1.1.1 — The add-on panel draws again on Blender 5.x. It asked for an icon named STACKED, which no longer exists, and a bad icon name aborts the whole draw — the MoCap AI tab came up empty, with nothing in it to click. Every icon name in the add-on is now checked against Blender's own list.