An image rendering method for an entertainment device for rendering a pixel at a viewpoint comprises the steps of, for a first element of a virtual scene, having a predetermined surface at a position within that scene, obtaining a machine learning system previously trained to predict a factor that, when combined with a distribution function that characterises an interaction of light with the predetermined surface, generates a pixel value corresponding to the first element of the virtual scene as illuminated at the position; providing the position and a direction based on the viewpoint to the machine learning system; combining the predicted factor from the machine learning system with the distribution function to generate the pixel value corresponding to the illuminated first element of the virtual scene at the position; and incorporating the pixel value into a rendered image for display; wherein the obtaining step comprises: identifying a current or anticipated state of an application determining the virtual scene to be rendered; requesting a download of a machine learning system corresponding to the current or anticipated state, from among a plurality of machine learning systems corresponding to a plurality of states of the application, accessible via a remote server; and downloading the requested machine learning system.