The possibility of using a neural network to perform super-resolution is discussed. A method is presented for mapping a regularized super-resolution cost function onto a neural network of the Hopfield type. The required computational effort is compared to conventional matrix-based approaches to super-resolution.
J B Abbiss,
B J Braves,
J S Bayley,
M A Fiddy,
"Super-Resolution And Neural Computing", Proc. SPIE 0880, High Speed Computing, (20 April 1988); doi: 10.1117/12.944042; https://doi.org/10.1117/12.944042