Digihuman is a project which aims to automatically generate whole body pose animation + facial animation on 3D Character models based on the camera input.
This project is my B.Sc thesis of Computer Engineering at Amirkabir University of Technology(AUT).
DigiHuman is a system for bringing automation in animation generation on 3D virtual characters.
It uses Pose estimation and facial landmark generator models to create entire body and face animation on 3D characters.
This project is done with MediaPipe and Unity3D.
MediaPipe generates 3D landmarks for the human whole body and face, and Unity3D is used to render the final animation after processing the generated landmarks from MediaPipe.
Do you want to support me in this project? :D
Follow the instructions to run the program!
- Install MediaPipe python.
pip install mediapipe
- Install OpenCV python.
pip install opencv-python
- Go to
backend
directory and install other requirements:
pip install -r requirements.txt
- You'll need to download the pretrained generator model for the COCO dataset and place it into
backend/checkpoints/coco_pretrained/
.
Install Unity3D and its requirements by the following guide lines(Skip 1-3 if Unity3D is already installed).
- Download and install UnityHub
- Add a new licence in UnityHub and register it
- Install a Unity Editor inside UnityHub(
LTS
versions and a version higher than2020.3.25f1
are recommended). - In the Unity project setting, allow HTTP connections in player setting.
- Download and import the following packages into your project to enable recording option available with FFmpeg(Download
.unitypackage
files and drag them to your project).
- FFmpegOut package (MIT license)
- FFmpegOutBinaries package (GPL)
- Run backend server at
backend
directory with the following command:python server.py
- Run Unity Project and open the main scene at
Assets\Scenes\MainScene.unity
- Test the program by uploading videos to backend from Unity project(You can test the application by selecting provided animations from the right side menu!).
You can add your own characters to the project!
Characters should have standard Humanoid rig to show kinematic animations. For rendering face animations, characters should have facial rig(Blendmesh).
Follow these steps to add your character:
- Find a 3D character model from Unity asset store or download a free one(You can download them from websites like Mixamo).
- Open the character setting and set the rig to humanoid
- Drag and drop your 3D charcter model to
CharacterChooser/CharacterSlideshow/Parent
object in Unity main Scene like the image below
- Add
BlendShapeController
andQualityData
components to character object in scene(which is dragged inside Parent object in last step). - Set
BlendShapeController
values
- Add character
SkinnedMeshRenderer
component toBlendShapeController
component.
- Find each blnedshape weight number under
SkinnedMeshRenderer
and set those numbers inBlendShapes
field insideBlendShapeController
(for specifying each blendshape value to theBlendShapeController
component so animation would be shown on character face by modification on these blendhape values)
- Open
CharacterSlideshow
Object onCharacterChooser/CharacterSlideshow
path inside scene hierachy, then add new dragged character to thenodes
property(all characters should be refrenced insidenodes
).
- Run the application and you can now select your character for rendering animation!
- Making full body animation
- Animating multiple blendshapes on 3D character (upto 40 blendshape animations is supported currently)
- Supporting any 3D models with Humanoid T-Pose rig
- Exporting animation in a video file
- Saving animation data and re-rendering it in future usages
- Filtering mediapipe outputs in order to detect and remove noises and better smoothness (Low Pass Filtering is used currently)
- Animating character face in high details
- Training a regression model to generate Blendmesh weights by feeding the output data of mediaPipe FaceMesh(468 points)
- Using StyleGan techniques to replace whole character face mesh
- Automatic rigging for 3D models without humanoid rig (Using deep neural network models like RigNet)
- Generating complete character mesh automatically using models like PIFuHD (in progress!)
- Animating 3D character mouth in high details using audio signal or natural language processing methods
- Generating complete environment in 3D
- Body Pose Estimation: BlazePose model
- Hands Pose Estimation: MediaPipe Hands model
- Face Detection: BlazeFace model
- Face Landmark Generator: MediaPipe Face Landmark Model
Application License: GPL-3.0 license Non-commercial use only.
- FFmpeg is licensed under the GNU Lesser General Public License (LGPL) version 2.1 or later. However, FFmpeg incorporates several optional parts and optimizations that are covered by the GNU General Public License (GPL) version 2 or later. If those parts get used the GPL applies to all of FFmpeg.
- Unity FFmpeg packages are licensed under Keijiro Takahashi MIT
- Used SPADE repository developed by NVIDIA and the customization is addapted from Smart-Sketch with GPL V 3.0 licence
@inproceedings{park2019SPADE,
title={Semantic Image Synthesis with Spatially-Adaptive Normalization},
author={Park, Taesung and Liu, Ming-Yu and Wang, Ting-Chun and Zhu, Jun-Yan},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2019}
}