Abstract: Data representing a scene is received. The scene includes labeled elements such as walls, a floor, a ceiling, and objects placed at various locations in the scene. The original received scene may be modified in different ways to create new scenes that are based on the original scene. These modifications include adding clutter to the scene, moving one or more elements of the scene, swapping one or more elements of the scene with different labeled elements, changing the size, color, or materials associated with one or more of the elements of the scene, and changing the lighting used in the scene. Each new scene may be used to generate labeled training data for a classifier by placing a virtual sensor (e.g., a camera) in the new scene, and generating sensor output data for the virtual sensor based on its placement in the new scene.

Abstract: Examples are disclosed that relate to computing devices and methods for simulating light passing through one or more lenses. In one example, a method comprises obtaining a point spread function of the one or more lenses, obtaining a first input raster image comprising a plurality of pixels, and ray tracing the first input raster image using the point spread function to generate a first output image. Based on ray tracing the first input raster image, a look up table is generated by computing a contribution to a pixel in the first output image, wherein the contribution is from a pixel at each location of a subset of locations in the first input raster image. A second input raster image is obtained, and the look up table is used to generate a second output image from the second input raster image.

Abstract: Examples are disclosed that relate to computing devices and methods for simulating light passing through one or more lenses. In one example, a method comprises obtaining a point spread function of the one or more lenses, obtaining a first input raster image comprising a plurality of pixels, and ray tracing the first input raster image using the point spread function to generate a first output image. Based on ray tracing the first input raster image, a look up table is generated by computing a contribution to a pixel in the first output image, wherein the contribution is from a pixel at each location of a subset of locations in the first input raster image. A second input raster image is obtained, and the look up table is used to generate a second output image from the second input raster image.

Abstract: Data representing a scene is received. The scene includes labeled elements such as walls, a floor, a ceiling, and objects placed at various locations in the scene. The original received scene may be modified in different ways to create new scenes that are based on the original scene. These modifications include adding clutter to the scene, moving one or more elements of the scene, swapping one or more elements of the scene with different labeled elements, changing the size, color, or materials associated with one or more of the elements of the scene, and changing the lighting used in the scene. Each new scene may be used to generate labeled training data for a classifier by placing a virtual sensor (e.g., a camera) in the new scene, and generating sensor output data for the virtual sensor based on its placement in the new scene.