Demo code for BlendshapeV2 3D avatar

PINTO0309 / PINTO_model_zoo

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

https://qiita.com/PINTO

MIT License

3.49k stars 566 forks source link

Demo code for BlendshapeV2 3D avatar #348

Closed royshil closed 1 year ago

royshil commented 1 year ago

Issue Type

Documentation Feature Request

OS

Windows

OS architecture

x86_64

Programming Language

C++, Python

Framework

ONNX

Model name and Weights/Checkpoints URL

Model name: BlendshapeV2

Description

Thanks for adding BlendshapeV2!

You have a demo of adding the 3D face using the landmarks from the model, I wonder if you can share that demo code? 🙏

Relevant Log Output

No response

URL or source code for simple inference testing code

No response

PINTO0309 commented 1 year ago

I only extracted and converted the models from this repository from which they were cited. Therefore, I have not written any code to render it, so I have nothing to share. Hopefully, you can parse MediaPipe's ultra-obscure source code, and I would love to see you issue a pull request to this repository (PINTO_model_zoo).

https://developers.google.com/mediapipe/solutions/vision/face_landmarker