Crowd-sourced video rendering system

Abstract

In one embodiment, a method includes distributing rendering tasks to connected client nodes having capable graphics processing units by transmitting viewport state data objects and a unique spatial location to each of the clients, performing path tracing at each of the clients from the starting point of their unique spatial locations, and transmitting their rendered output back to the server. The server generates a composite rendered output from the individual rendered outputs received by the participating clients, and then transmits the composite to all connected clients for display. Thus, as the number of client nodes increases, the scene is rendered more rapidly and at higher quality. In particular embodiments, the rendered output is a lightmap representing the diffuse lighting for the scene, and each client may render the scene's specular highlights from its own viewport.