Abstract: In one aspect, a method is performed by one or more processors. The method includes receiving a primary view image showing a scene from a view of a primary camera; depth values for one or more objects in the scene; and a camera offset between the primary camera and a secondary camera. The method further includes determining disparities for each pixel in the primary view image. The method further includes generating a secondary view image using the primary view image, the depth values, and the camera offset. At least some of the pixels are repositioned according to the determined disparities.

Abstract: A method performed by one or more processors includes: receiving model data defining a three-dimensional scene; rendering the three-dimensional scene into a primary view image showing the three-dimensional scene from a view of a primary camera; and generating, for each of at least some pixels in the primary view image, a disparity value that defines a disparity between a location of the pixel in the primary view image and an indicated location of the pixel in a secondary view image showing the three-dimensional scene from a view of a secondary camera.