Method and non-transitory computer readable storage medium for video generative compression

1 . A method of decoding a bitstream to get one or more pictures for a video stream, the method comprising:

receiving a bitstream; and

decoding the bitstream to get the one or more pictures,

wherein the decoding comprises:

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;

wherein the bitstream comprises a picture unit delimiter (PUD) indicating that following NAL units belong to a next picture unit.

2 . The method according to claim 1 , wherein the key picture is decoded by the decoder based on the receiving bitstream.

3 . The method according to claim 1 , wherein the key picture and the one or more SEI message are in a same picture unit.

4 . The method according to claim 2 , wherein a first picture unit comprises one SEI message, and a second picture unit comprises the key picture.

5 . The method according to claim 4 , wherein the first picture unit further comprises a coded slice network abstraction layer (NAL) unit for a coded picture.

6 . The method according to claim 5 , further comprising:

decoding the coded picture to obtain a decoded picture;

generating a picture based on the key picture and the SEI messages contained in the first picture unit; and

outputting the generated picture instead of the decoded picture.

7 . The method according to claim 1 , further comprising:

decoding a flag in the PUD indicating whether the following picture unit is an intra random access point (IRAP) picture unit or a gradual decoding refresh (GDR) picture unit; and

decoding an index in the PUD indicating a picture type of a coded picture in the following picture unit.

8 . A method of encoding a video sequence into a bitstream, the method comprising:

receiving a video sequence;

encoding one or more pictures of the video sequence; and

generating a bitstream,

wherein the encoding comprises:

encoding one or more supplemental enhancement information (SEI) messages corresponding to one or more pictures, respectively; and

encoding the one or more SEI messages in a picture unit;

wherein the bitstream comprises a picture unit delimiter (PUD) indicating that following NAL units belong to a next picture unit.

9 . The method according to claim 8 , wherein the encoding further comprises:

encoding a key picture in the picture unit.

10 . The method according to claim 8 , wherein the encoding further comprising:

encoding one SEI message in a first picture unit; and

encoding a key picture in a second picture unit.

11 . The method according to claim 10 , wherein the encoding further comprises:

encoding a slice network abstraction layer (NAL) unit for a picture in the first picture unit.

12 . The method according to claim 8 , wherein the encoding further comprises:

encoding a flag in the PUD to indicate whether the following picture unit is an intra random access point (IRAP) picture unit or a gradual decoding refresh (GDR) picture unit; and

encoding an index in the PUD to indicate a picture type of a coded picture in the following picture unit.

13 . The method according to claim 8 , further comprising:

storing the bitstream that is generated based on the encoding.

14 . A method for signaling a bitstream, the method comprising:

receiving a video sequence;

encoding the video sequence by:

encoding one or more supplemental enhancement information (SEI) messages corresponding to one or more pictures, respectively; and

encoding the one or more SEI messages in a picture unit; and

signaling a bitstream that is generated based on the encoding;

wherein the bitstream comprises a picture unit delimiter (PUD) indicating that following NAL units belong to a next picture unit.

15 . The method according to claim 14 , wherein the encoding further comprises:

encoding a key picture in the picture unit.

16 . The method according to claim 14 , wherein the encoding further comprising:

encoding one SEI message in a first picture unit; and

encoding a key picture in a second picture unit.

17 . The method according to claim 16 , wherein the encoding further comprises:

encoding a slice network abstraction layer (NAL) unit for a picture in the first picture unit.

18 . The method according to claim 14 , wherein the encoding further comprises:

encoding a flag in the PUD to indicate whether the following picture unit is an intra random access point (IRAP) picture unit or a gradual decoding refresh (GDR) picture unit; and

encoding an index in the PUD to indicate a picture type of a coded picture in the following picture unit.