Method and non-transitory computer readable storage medium for video generative compression
AssigneeAlibaba Innovation Private Limited
InventorsJie CHEN, Yan YE, Bolin CHEN
Life of this patent
Estimating the term…
Abstract
A method of decoding a bitstream to get one or more pictures for a video stream includes: receiving a bitstream; and decoding the bitstream to get the one or more pictures. The decoding includes: decoding a picture unit comprising one or more supplemental enhancement information (SEI) messages; and generating the one or more pictures based on a key picture and the one or more SEI messages, respectively.
Claims17
A method of decoding a bitstream to obtain one or more pictures, the method comprising:
- receiving a bitstream;
- decoding, from the bitstream, one or more Supplemental Enhancement Information (SEI) messages, wherein each SEI message comprises a parameter indicating a count of the SEI message within a picture unit;
- generating one or more pictures based on the one or more SEI messages, wherein each picture of the one or more pictures being generated based on a respective SEI message of the decoded one or more SEI messages;
- and
- outputting the one or more generated pictures based on the count in the one or more SEI messages.
A method of encoding a video sequence into a bitstream, the method comprising:
- receiving a video sequence having one or more pictures;
- encoding one or more supplemental enhancement information (SEI) messages corresponding to the one or more pictures, respectively, wherein each SEI message comprises a parameter indicating a count of the SEI message within a picture unit.
A method for transmitting a bitstream, the method comprising:
- receiving a video sequence having one or more pictures;
- encoding one or more supplemental enhancement information (SEI) messages corresponding to the one or more pictures, respectively, wherein each SEI message comprises a parameter indicating a count of the SEI message within a picture unit;
- and
- transmitting a bitstream that is generated based on the encoding.
Dependencies are inferred from the claim text.