MPAI-PAF V1.6 AIMs Scene and Avatar Rendering

Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance

1 Functions

The Scene and Avatar Rendering (PAF‑SAR) AIM places a Speaking Avatar, at the Avatar Point of View, in a Basic Multimodal Scene seen and heard from the Point of View. It produces the Scene as data, either as a Basic Audio Scene (the Avatar speech among the Audio of the Scene) and a Basic Visual Scene (what is seen, as 2D Visual Objects), or as the Basic Multimodal Scene and the 3D Model Scene with the Avatar placed. It does not play or draw: the Scene is played or drawn by whoever receives it:

Receives	Speaking Avatar	The Speaking Avatar to be placed in the Scene.
	Point of View	The Point of View from which the Scene is seen and heard (optional).
	Multimodal Scene	The Scene in which the Speaking Avatar is placed (optional).
	Avatar PoV	The Point of View at which the Speaking Avatar is placed (optional).
Produces	Audio Scene	The Audio of the Scene with the Avatar speech (optional).
	Visual Scene	What is seen from the Point of View, as 2D Visual Objects (optional).
	Multimodal Scene	The Scene with the Speaking Avatar placed (optional).
	3D Model Scene	The 3D Model Scene with the Avatar placed (optional).

2 Reference Model

Figure 1 depicts the Reference Model of the Scene and Avatar Rendering (PAF‑SAR) AIM.

Figure 1 – The Scene and Avatar Rendering (PAF‑SAR) AIM

3 I/O Data

Table 1 specifies the Input and Output Data of the Scene and Avatar Rendering (PAF‑SAR) AIM.

Table 1 – I/O Data of the Scene and Avatar Rendering (PAF‑SAR) AIM

Input	Description
Speaking Avatar	The Speaking Avatar to be placed in the Scene.
Point of View	The Point of View from which the Scene is seen and heard (optional).
Multimodal Scene	The Scene in which the Speaking Avatar is placed (optional).
Avatar PoV	The Point of View at which the Speaking Avatar is placed (optional).
Output	Description
Audio Scene	The Audio of the Scene with the Avatar speech (optional).
Visual Scene	What is seen from the Point of View, as 2D Visual Objects (optional).
Multimodal Scene	The Scene with the Speaking Avatar placed (optional).
3D Model Scene	The 3D Model Scene with the Avatar placed (optional).

4 SubAIMs

No SubAIMs.

5 JSON Metadata

https://schemas.mpai.community/PAF/V1.6/AIMs/SceneAndAvatarRendering.json

6 Profiles

No Profiles.

7 Reference Software

Not part of this specification.

8 Conformance Testing

Table 2 provides the Conformance Testing Method for the PAF‑SAR AIM.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present, and conform with the Qualifier, if present.

Table 2 – Conformance Testing Method for the PAF‑SAR AIM

Receives	Speaking Avatar	Shall validate against Speaking Avatar schema.
	Point of View	Shall validate against Point of View schema.
	Multimodal Scene	Shall validate against Basic Multimodal Scene schema.
	Avatar PoV	Shall validate against Point of View schema.
Produces	Audio Scene	Shall validate against Basic Audio Scene schema.
	Visual Scene	Shall validate against Basic Visual Scene schema.
	Multimodal Scene	Shall validate against Basic Multimodal Scene schema.
	3D Model Scene	Shall validate against Basic 3D Model Scene schema.

9 Performance Assessment