Awesome
<p align="center"> <a href="" rel="noopener"> <img style=vertical-align:middle; height=150px src="resources/blender_community_badge_white.png" alt="Blender logo"></a> </p> <h1 align="center">VOCA Blender Addon</br><sub></sub></h1>π Table of Contents
πAbout <a name = "about"></a>
<p align="center" > <img width=80% src="resources\voca_blender_animation.gif" alt="Voca gif"></a> </p> VOCA is a simple and generic speech-driven facial animation framework that works across a range of identities. This add-on integrates VOCA withing Blender and allows the user to:- Run VOCA and synthesize a character animation given an speech signal. VOCA outputs a set meshes with .obj extension which must to be imported.
- Import the output meshes of VOCA and generate from them a single animated mesh.
For more details please see the scientific publication of the VOCA framework here.
The original VOCA framework repository can be found here here.
π©βπ»Installation and Usage <a name="ins-usage"></a>
- The add-on works with \Blender v2.92.0 (python 3.7) and requires some dependencies that can be installed directly from the preferences panel.
- Download the latest release.
- Import the downloaded .zip archive in Blender (Edit > Preferences > Add-ons > Install) and enable the add-on.
- Install the dependencies by clicking the dedicated button
- The add-on options are accessible in the 3D View side panel named "VOCA"
- (optional) If you want to uninstall the addon, you can also uninstall the dependencies from the preferences panel.
To generate a new sequence of meshes:
- Expand the 'Run VOCA Model' panel.
- Select the right path for the mesh template (.ply) to animate, the audio file with the speech signal and the desired output directory.
- Hit 'Run' and wait the end of the process.
To import the VOCA-generated meshes and generate the animated mesh:
- Expand the 'Import Mesh' panel.
- Select the path to the audio file and the output directory.
- Hit 'Import' and wait.
The 'Dev' panel allows you to:
- Hide/unhide non-VOCA meshes.
- Remove all meshes from the scene.
- Remove all non-VOCA meshes from the scene.
- Edit sequences (flame parameters: head, pose, blink)
π Project Topology <a name="project-topology"></a>
voca-blender/
ββ voca-addon/
β ββ audio/
β β ββ sentence20.wav
β β ββ test_sentence.wav
β ββ flame/
β β ββ generic_model.pkl
β ββ model/
β β ββ gstep.model.*
β ββ smpl_webuser/
β β ββ lbs.py
β β ββ posemapper.py
β β ββ serialization.py
β β ββ verts.py
β ββ template/
β β ββ FLAME_sample.ply
β ββ utils/
β | ββ ctypesloader.py
β β ββ audio_handler.py
β β ββ edit_sequences.py
β β ββ inference.py
β ββ operators.py
β ββ panels.py
β ββ __init__.py
ββ install-dependencies.command
ββ install-dependencies.sh
ββ LICENSE
ββ README.md
βοΈ Authors <a name = "authors"></a>
- Conti Edoardo @edoardo-conti
- Federici Lorenzo @lorenzo-federici
- Melnic Andrian @andrian-melnic
π Acknowledgements <a name = "acknowledgement"></a>
- Computer Graphics e Multimedia Class - Professor <a href="https://vrai.dii.univpm.it/primo.zingaretti"><i>Primo Zingaretti</i></a>