-
Notifications
You must be signed in to change notification settings - Fork 14
Generating New Facial expressions
Brice Donval edited this page Jan 7, 2020
·
6 revisions
-
The Face Library Viewer module allows to create a facial expression, using configurable Action Units. These AUs are classified as follows :
- Upper Face AUs (eyebrows and eyelids...)
- Lower Face - Up / Down / Horizontal (Mouth openness or stretch...)
- Lower Face - Oblique / Orbital (Smile and other mouth configuration...)
- Misc (nose and cheek...)
-
By varying the values for different combinations of Action Units, we can create new facial expressions in the virtual agent. For example, to create the expression for 'surprise', the action units involved are 1,2,5 and 26. Refer to the following table to create any of these emotions in the virtual character's face.
- To compose a new facial expression, add the FaceLibrary Viewer module to the agent configuration window. You can find it in the configuration window under the 'ADD'; tab inside 'Tools' category.
- Connect it to the "Simple AU Performer" (Add / AU Performers / Simple AU Performer). In the off-the-shelf module, it is already available with as the "AU to FAP" node
- You can start editing the FaceLibraryViewer by changing the AU values interactively. Don't forget to save your modification. You can also create new ones.
- The new facial expression will be saved in
<GRETA_DIR>/bin/BehaviorRealizer/facelibrary.xml
. - You can also specify the intensity for each AU manually by modifying the file.
<expression class="faceexp" instance="new_expression1">
<action name="AU1"/>
<action name="AU2"/>
<action name="AU5"/>
<action intensity="0.5" name="AU25"/>
</expression>
- Whenever you do a change in a Library, you need to reload the Greta-Platform to be able to manipulate it. Libraries are loaded into the system only when it is first run.
Advanced
- Generating New Facial expressions
- Generating New Gestures
- Generating new Hand configurations
- Torso Editor Interface
- Creating an Instance for Interaction
- Create a new virtual character
- Creating a Greta Module in Java
- Modular Application
- Basic Configuration
- Signal
- Feedbacks
- From text to FML
- Expressivity Parameters
- Text-to-speech, TTS
-
AUs from external sources
-
Large language model (LLM)
-
Automatic speech recognition (ASR)
-
Extentions
-
Integration examples
Nothing to show here