Encoding digital content based on models for predicting similarity between exemplars

A computer program product having a non-transitory computer-readable storage medium storing computer-executable code for determining a predictor block for encoding an input block of digital content, the code comprising:

• an encoder module configured to:
• receive a target block of digital content for encoding;
• obtain a plurality of clusters of exemplars by applying one or more prediction models to the target block, each prediction model mapping blocks of digital content to clusters of similar exemplars;
• determine a frequency of occurrence of exemplars in the plurality of clusters;
• select a predictor block for encoding the target block based on criteria including the frequency of occurrence of exemplars in the plurality of clusters;
• and
• encode the target block using the predictor block.

A computer-implemented system for determining a predictor block for encoding an input block of digital content, the system comprising:

• a computer processor;
• and
• a computer-readable storage medium storing computer program modules configured to execute on the computer processor, the computer program modules comprising:
• an encoder module configured to:
• receive a target block of digital content for encoding;
• obtain a plurality of clusters of exemplars by applying one or more prediction models to the target block, each prediction model mapping blocks of digital content to clusters of similar exemplars;
• determine a frequency of occurrence of exemplars in the plurality of clusters;
• select a predictor block for encoding the target block based on criteria including the frequency of occurrence of exemplars in the plurality of clusters;
• and
• encode the target block using the predictor block.