摘要 |
A mechanism is described for facilitating efficient computation for hybrid camera arrays at computing devices according to one embodiment. A method of embodiments, as described herein, includes selecting a camera to serve as a reference camera, where the camera is selected from a plurality of cameras in a hybrid camera array, performing matching across images obtained from multiple camera pairs of the plurality of cameras, and selecting one or more best camera pairs of the multiple camera pairs based on at least one of placement, type, and history associated with each camera of the multiple camera pairs. |