Sampling across multiple views in supersampling operation

One or more computer-readable storage mediums having stored thereon executable computer program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• generating frames of image data generated for a plurality of views of a rendered scene in a graphics system;
• receiving for processing in the graphics system a first current frame including first image data generated for a first view of the plurality of views and a second current frame including second image data generated for a second view of the plurality of views;
• and
• performing supersampling processing utilizing one or more neural networks based on at least the first current frame and the second current frame and one or more prior generated frames for each of the plurality of views.

A method comprising:

• generating frames for a plurality of views of a rendered scene in a graphics system;
• receiving for processing in the graphics system a first current frame including first image data generated for a first view of the plurality of views and a second current frame including second image data generated for a second view of the plurality of views;
• and
• performing supersampling processing utilizing one or more neural networks based on at least the first current frame and the second current frame and one or more prior generated frames for each of the plurality of views.