Region-based processing of predicted pixels

A method for decoding a compressed video data sequence, comprising:

• buffering the compressed video sequence, the compressed video sequence comprising one or more coded pixel blocks;
• reviewing prediction information of the one or more coded pixel blocks;
• grouping coded pixel blocks based on the reviewed prediction information, the coded pixel blocks within a group having similar prediction dependencies;
• scheduling decoding of the pixel blocks according to the grouping;
• and
• decoding the scheduled groups of coded pixel blocks to produce a decoded video data sequence.

A computer-readable memory having stored thereon a plurality of instructions for decoding a compressed video sequence comprising one or more coded pixel blocks, which when executed by a processor, cause the processor to:

• retrieve coding parameters of a coded pixel block;
• compare the coding parameters of the coded pixel block to coding parameters of a current group of pixel blocks;
• add the coded pixel block to the current group of pixel blocks if the coding parameters of the coded pixel block match the coding parameters of the current group of pixel blocks;
• and
• schedule decoding of the current group of pixel blocks once the current group of pixel blocks is closed, wherein the current group of pixel blocks is closed upon detection of a first non-qualifying coded pixel block.

A method for encoding a video data sequence, comprising:

• coding the video data sequence to generate a coded video sequence comprising one or more coded pixel blocks;
• reviewing prediction information for each of the one or more coded pixel blocks;
• forming one or more groups of coded pixel blocks based on the reviewed prediction information, the coded pixel blocks within a group having similar prediction dependencies;
• associating a group identifier with each group of coded pixel blocks to form a formatted coded video data sequence.

A method for decoding a compressed video data sequence, comprising:

• buffering the compressed video sequence, the compressed video sequence comprising one or more coded pixel blocks;
• reviewing prediction information of the one or more coded pixel blocks;
• grouping coded pixel blocks based on the reviewed prediction information, the coded pixel blocks within a group independent of a reconstructed pixel within the group;
• scheduling decoding of the pixel blocks according to the grouping;
• and
• decoding the scheduled groups of coded pixel blocks to produce a decoded video data sequence.

A method for encoding a video data sequence, comprising:

• coding the video data sequence to generate a coded video sequence comprising one or more coded pixel blocks;
• reviewing prediction information for each of the one or more coded pixel blocks;
• forming one or more groups of coded pixel blocks based on the reviewed prediction information, the coded pixel blocks within a group independent of a reconstructed pixel within the group;
• associating a group identifier with each group of coded pixel blocks to form a formatted coded video data sequence.