Multi-perspective stereoscopy from light fields

A system comprising:

• one or more processors configured to:
• generate a respective depth map for each of a set of computer-generated input images of a scene;
• generate a depth volume from the generated depth maps, the depth volume corresponding to a three-dimensional (3D) representation of a light field representing light rays from the scene;
• determine a plurality of two-dimensional (2D) subsets of the depth volume corresponding to a plurality of 2 D subsets of the 3 D representation of the light field, wherein at least one 2 D subset of the depth volume corresponds to a cut by non-planar surface with the depth volume;
• determine a plurality of the computer-generated input images whose respective depth maps are included in the determined 2 D subsets of the depth volume;
• and
• render, by a computer system, the determined plurality of the computer-generated input images.

A non-transitory computer-readable medium containing program code that, when executed by a computer, causes the computer to perform a method of deferred rendering of computer-generated content comprising:

• generating a respective depth map for each of a set of computer-generated input images of a scene;
• generating a depth volume from the generated depth maps, the depth volume corresponding to a three-dimensional (3D) representation of a light field representing light rays from the scene;
• determining a plurality of two-dimensional (2D) subsets of the depth volume corresponding to a plurality of 2 D subsets of the 3 D representation of the light field, wherein at least one 2 D subset of the depth volume corresponds to a cut by non-planar surface with the depth volume;
• determining a plurality of the computer-generated input images whose respective depth maps are included in the determined 2 D subsets of the depth volume;
• and
• rendering, by a computer system, the determined plurality of the computer-generated input images.