A Hardware Realization of Superresolution Combining Random Coding and Blurring

Resolution enhancements are often desired in imaging applications where high-resolution sensor arrays are difficult to obtain. Many computational imaging methods have been proposed to encode high-resolution scene information on low-resolution sensors by cleverly modulating light from the scene before it hits the sensor. These methods often require movement of some portion of the imaging apparatus or only acquire images up to the resolution of a modulating element. Here a technique is presented for resolving beyond the resolutions of both a pointwise-modulating mask element and a sensor array through the introduction of a controlled blur into the optical pathway. The analysis contains an intuitive and exact expression for the overall superresolvability of the system, and arguments are presented to explain how the combination of random coding and blurring makes the superresolution problem well-posed. Experimental results demonstrate that a resolution enhancement of approximately $4\times$ is possible in practice using standard optical components, without mechanical motion of the imaging apparatus, and without any a priori assumptions on scene structure.