Region-based processing of predicted pixels
AssigneeApple Inc.
InventorsThomas Pun, Paul Chang, Hsi-Jung Wu
Life of this patent
Estimating the term…
Abstract
A method for decoding a compressed video data sequence containing one or more coded pixel blocks. The compressed video sequence is buffered. Prediction information for each of the coded pixel blocks is reviewed. One or more groups of coded pixel blocks are formed based on the reviewed prediction information such that the coded pixel blocks within a given group have similar prediction dependencies and/or at least do not depend on a reconstructed pixel within a group of received pixel blocks to enable parallel decoding. The formed groups are scheduled for processing and subsequently decoded to produce a decoded video data sequence.
Claims23
A method for decoding a compressed video data sequence, comprising:
- buffering the compressed video sequence, the compressed video sequence comprising a plurality of coded pixel blocks;
- identifying, from a syntax element of the compressed video sequence, groups of adjacent blocks from the coded pixel blocks that share a common reference frame and can be decoded in parallel from each other;
- organizing the coded pixel blocks according to the groups based on the syntax element;
- scheduling decoding of the coded pixel blocks on a group-by-group basis;
- and
- decoding the groups of coded pixel blocks according to the group-by-group schedule to produce a decoded video data sequence, wherein the decoding of each pixel block in a group uses content from the common reference frame for the respective group.
A non-transitory 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:
- buffer the compressed video sequence, the compressed video sequence comprising a plurality of coded pixel blocks;
- identify, from a syntax element of the compressed video sequence, groups of adjacent blocks from the coded pixel blocks that share a common reference frame and can be decoded in parallel from each other;
- organize the coded pixel blocks according to the groups based on the syntax element;
- schedule decoding of the coded pixel blocks on a group-by-group basis;
- and
- decode the groups of coded pixel blocks according to the group-by-group schedule to produce a decoded video data sequence, wherein the decoding of each pixel block in a group uses content from the common reference frame for the respective group.
A method for encoding a video sequence, comprising:
- coding data from a video source according to a coding protocol, wherein the coded data identifies
- by a syntax element of the coding protocol, groups of adjacent blocks from the coded pixel blocks that share a common reference frame and can be decoded in parallel from each other and the encoding of the respective group comprises decoding each pixel block in the group using content from the common reference frame;
- transmitting the coded data to a decoder device.
A method for decoding a compressed video data sequence, comprising:
- buffering the compressed video sequence, the compressed video sequence comprising a plurality of coded pixel blocks;
- identifying, from a syntax element of the compressed video sequence, groups of the coded pixel blocks that share a common reference frame and can be decoded in parallel from each other;
- scheduling decoding of the coded pixel blocks on a group-by-group basis;
- and
- decoding the groups of coded pixel blocks according to the group-by-group schedule to produce a decoded video data sequence, wherein the decoding of each pixel block in a group uses content from the common reference frame for the respective group.
Dependencies are inferred from the claim text.