Image synthesis

An apparatus comprising:

• a receiver circuit, wherein the receiver circuit is arranged to receive a data stream, wherein the date stream comprises:
• image data for a plurality of images of the scene, wherein the plurality of images of the scene represent a scene captured from different view poses;
• three dimensional spatial data for the scene;
• and
• coefficient data describing coefficients for a view synthesis neural network circuit;
• wherein the view synthesis neural network circuit, wherein the view syntheses neural network circuit is arranged to generate view shifted images of the scene for different view poses from the plurality of images of the scene and the three dimensional spatial data;
• and
• a neural network controller circuit, wherein the view syntheses neural network circuit is arranged to set coefficients of the neural network in response to the coefficient data.

A method for generating audio visual data stream, the method comprising:

• receiving a plurality of images of a scene, wherein the scene is captured from different view poses;
• receiving three dimensional spatial data of the scene;
• generating view shifted images for the scene for different view poses from the plurality of images of the scene and the three dimensional spatial data, wherein the generating uses a view syntheses neural network;
• training the view synthesis neural network based on images of the scene for different view poses;
• and
• generating a data stream, wherein the data stream comprises:
• image data for at least one of the plurality of images of the scene;
• scene data, wherein the scene data represents the three dimensional spatial data;
• and
• coefficient data, wherein the coefficient data describes coefficients of the view synthesis neural network circuit after training.

A method comprising:

• receiving a data stream, wherein the date stream comprises:
• image data for a plurality of images of the scene, wherein the plurality of images of the scene represent a scene captured from different view poses;
• three dimensional spatial data for the scene;
• and
• coefficient data describing coefficients for a view synthesis neural network circuit;
• generating view shifted images of the scene for different view poses from the plurality of images of the scene and the three dimensional spatial data, using a view synthesis neural network;
• and
• setting coefficients of the view synthesis neural network in response to the coefficient data.

An apparatus comprising:

• a processor circuit and a memory circuit, wherein the memory is arranged to store instructions for the processor circuit,
• wherein the processor circuit is arranged to receive a plurality of images of a scene, wherein the scene is captured from different view poses,
• wherein the processor circuit is arranged to receive three dimensional spatial data of the scene,
• wherein the processor circuit is arranged to generate view shifted images for the scene for different view poses from the plurality of images of the scene and the three dimensional spatial data using a view syntheses neural network,
• wherein the processor circuit is arranged to train the view synthesis neural network based on images of the scene for different view poses,
• wherein the processor circuit is arranged to generate a data stream, wherein the data stream comprises:
• image data for at least one of the plurality of images of the scene;
• scene data, wherein the scene data represents the three dimensional spatial data;] and
• coefficient data, wherein the coefficient data describes coefficients of the view synthesis neural network circuit after training.

An apparatus comprising:

• a processor circuit and a memory circuit, wherein the memory is arranged to store instructions for the processor circuit,
• wherein the processor circuit is arranged to receive a data stream, wherein the date stream comprises:
• image data for a plurality of images of the scene, wherein the plurality of images of the scene represent a scene captured from different view poses;
• three dimensional spatial data for the scene;
• and
• coefficient data describing coefficients for a view synthesis neural network circuit;
• wherein the processor circuit is arranged to generate view shifted images of the scene for different view poses from the plurality of images of the scene and the three dimensional spatial data using a view synthesis neural network,
• wherein the processor circuit is arranged to set coefficients of the view synthesis neural network in response to the coefficient data.