Image generation system and method

1. An image generation system comprising:

an image rendering unit operable to render a first image for display to a first one of a user's eyes;

an image obtaining unit operable to obtain a second image for a second one of the user's eyes, the obtained image having been rendered for display at an earlier time;

an image reprojection unit operable to reproject the first image from a viewpoint associated with the first one of the user's eyes to a viewpoint associated with the second one of the user's eyes; and

an image generation unit operable to generate an output image for the second one of the user's eyes in dependence upon the reprojected first image and the obtained second image.

2. The system of claim 1 , wherein the image rendering unit is operable to render one or more image portions corresponding to missing image areas in the reprojected image.

3. The system of claim 1 , wherein the image generation system is configured to generate a first image for the first one of the user's eyes at a first time, and a second image for the second one of the user's eyes at a second time.

4. The system of claim 3 , wherein the first image and the second image are successive image frames for display as a part of a video content.

5. The system of claim 3 , wherein a group of two or more images for the first one of the user's eyes are generated before generating a group of two or more images for the second one of the user's eyes.

6. The system of claim 1 , comprising an image analysis unit operable to identify one or more portions of the rendered image for the first one of the user's eyes for which a standard rendering process should be used to generate corresponding portions of the output image.

7. The system of claim 6 , wherein the one or more portions are objects that are identified as having an equal to or above threshold motion, complexity, or rotation.

8. The system of claim 6 , wherein the one or more portions are portions that are only able to be seen from a viewpoint corresponding to a single one of the user's eyes.

9. The system of claim 1 , wherein the image generation unit is operable to utilise a trained machine learning model to generate the output image.

10. The system of claim 9 , wherein the machine learning model is trained for a particular interactive game or interactive video content, or a portion thereof.

11. The system of claim 1 , wherein at least the image rendering unit is located at a first device and at least the image generation unit is located at a second device.

12. The system of claim 1 , wherein the first image and the output image are output for simultaneous display at a head-mountable display device.

13. An image generation method comprising:

rendering a first image for display to a first one of a user's eyes;

obtaining a second image for a second one of the user's eyes, the obtained image having been rendered for display at an earlier time;

reprojecting the first image from a viewpoint associated with the first one of the user's eyes to a viewpoint associated with the second one of the user's eyes; and

generating an output image for the second one of the user's eyes in dependence upon the reprojected first image and the obtained second image.

14. A non-transitory machine-readable storage medium which stores computer software which, when executed by a computer, causes the computer to perform an image generation method comprising the steps of:

rendering a first image for display to a first one of a user's eyes;

obtaining a second image for a second one of the user's eyes, the obtained image having been rendered for display at an earlier time;

reprojecting the first image from a viewpoint associated with the first one of the user's eyes to a viewpoint associated with the second one of the user's eyes; and

generating an output image for the second one of the user's eyes in dependence upon the reprojected first image and the obtained second image.