| 1 Function | 2 Reference Model | 3 Input/Output Data |
| 4 SubAIMs | 5 JSON Metadata | 6 Profiles |
| 7 Reference Software | 8 Conformance Texting | 9 Performance Assessment |
1 Functions
Visual Scene Creation (PAF-VSC):
| Receives | Avatar ID |
| Audio-Visual Scene Descriptors | |
| Avatar Model | |
| Spatial Attitude | |
| Body Descriptors | |
| Face Descriptors | |
| Produces | Visual Scene Descriptors |
| Spatial Attitude of Avatars’ Mouths |
2 Reference Model
Figure 1depicts the Reference Architecture of the PS-Face Interpretation AIM.
Figure 1– The Visual Scene Creation (PAF-VSC) AIM
3 Input/Output Data
Table 1specifies the Input and Output Data of the Visual Scene Creation (PAF-VSC) AIM.
Table 1– I/O Data of the Visual Scene Creation (PAF-VSC) AIM
| Input | Description |
| Avatar IDs | IDs of Participants’ and MVS’ Avatars |
| Audio-Visual Scene Descriptors | Descriptors of the Initial Visual Scene |
| Avatar Models | Models of Participants’ and VMS’ Avatars |
| Spatial Attitudes | Spatial Attitudes of Participants’ and VMS’ Avatars |
| Body Descriptors | Body Descriptors of Participants’ and VMS’ Avatars |
| Face Descriptors | Face Descriptors of Participants’ and VMS’ Avatars |
| Speech Objects | Speech Objects of Participants’ and VMS’ Avatars |
| Text Objects | Text Objects of Participants’ and VMS’ Avatars |
| Output | Description |
| Visual Scene Descriptors | Descriptors of the entire Visual Scene |
| Mouth Spatial Attitudes | The Spatial Attitudes of the Mouths of Participants’ and VMS’ Avatars |
4 SubAIMs
No SubAIMs.
5 JSON Metadata
https://schemas.mpai.community/PAF/V1.2/AIMs/VisualSceneCreation.json
6 Profiles
No Profiles
7 Reference Software
8 Conformance Testing
9 Performance Assessment
