An apparatus has a pixel array, a multi-lens array (MLA) coupled to the pixel array, and circuitry functionally coupled to the pixel array. The pixel array has a plurality of pixels for receiving-and-displaying or sensing-and-outputting a plurality of elemental images. The MLA has a plurality of lenslets. The circuitry has a model for processing the plurality of elemental images. The model and one or more characteristics of the plurality of lenslets are jointly optimized.