Unity VRM Live Face Overlay

I already have a complete .vrm avatar; what it lacks is my real-world expression. Your task is to build a Unity scene that takes a live webcam feed, tracks only my eyes and mouth, and projects them onto the model in real time so the character blinks, looks and speaks with my actual features.

The workflow I have in mind is straightforward:
1. Unity (latest LTS) loads the .vrm file through UniVRM.
2. A webcam stream is processed on the fly—OpenCV, MediaPipe, or any other lightweight library you prefer—to isolate eye and mouth regions.
3. Those regions are then composited onto the avatar’s existing eye and mouth meshes or UVs with minimal latency, keeping head pose from the original rig intact.

Deliverables
• A self-contained Unity project or package with clearly commented C# scripts.
• A short calibration routine so I can line up the tracking once and save the offsets.
• Simple UI toggle to start/stop the overlay and switch back to the default textures.
• Quick README or screen-share video that shows setup, play-mode demo, and how to replace the webcam if I upgrade hardware later.

Acceptance criteria
• Overlay stays locked during normal talking and blinking, under 70 ms end-to-end latency.
• Works on a standard 1080p webcam without additional hardware.
• No noticeable artifacts when the avatar turns ±30° on the Y-axis.

If you have prior VTuber or AR face-tracking examples, feel free to share when you bid so I can gauge fit. I’m ready to test builds as soon as you have a prototype.