IP Library Granted Patent US 12707093
Granted Patent B2
US 12707093 · App. 18/895,594 · Granted Aug 11, 2026

SEI message for film grain synthesis

Inventors: Stephan Wenger (Palo Alto, CA); Arianne Hinds (Palo Alto, CA)
Assignee: TENCENT AMERICA LLC
H04N19/70H04N19/132H04N19/136H04N19/167H04N19/172
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12707093
App. No.
18/895,594
Granted
Aug 11, 2026
Kind
B2
Abstract

A method and apparatus comprising computer code configured to cause a processor or processors to obtain video data comprising at least one coded picture, reconstruct a coded picture including a film grain characteristics SEI message, an alpha channel information SEI message, and at least a first sample and a second sample and at least a third alpha map sample and a fourth alpha map sample, wherein after reconstruction the first sample and the third alpha map sample, and the second sample and first sample are spatially co-located; apply film grain synthesis to the first sample based on a first value of the third sample; and determine to not applying film grain syntheses to the second sample based on a second value of the fourth sample, wherein the first value and second value are different from each other.

Claims (64)

1 . A method for video decoding, the method comprising:

obtaining video data comprising at least one coded picture;

reconstructing a coded picture comprising a film grain characteristics SEI message, an alpha channel information SEI message, and at least a first sample and a second sample and at least a third alpha map sample and a fourth alpha map sample, after reconstruction the first sample and the third alpha map sample, and the second sample and the fourth alpha map sample are spatially co-located, and the film grain characteristics SEI message:

specifies coordinates of a top-left corner and a width and a height of a bounding box of an i-th region of a picture by any of an for region_top[i] syntax, an for region left[i] syntax, an for region width[i] syntax, and an for region height[i] syntax, and any of:

a value of the fgr_region_top[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicWidthInLumaSamples−1, inclusive,

a value of the fgr_region left[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicHeightInLumaSamples−1, inclusive,

a value of the fgr_region width[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicWidthInLumaSamples−for region left[i], inclusive, and

a value of the for region height[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicHeightInLumaSamples−fgr_region_top[i], inclusive;

applying film grain synthesis to the first sample based on a first value of the third sample; and

determining to not apply film grain synthesis to the second sample based on a second value of the fourth sample, wherein the first value and second value are different from each other.

2 . The method according to claim 1 , wherein each of:

the value of the fgr_region_top[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicWidthInLumaSamples−1, inclusive,

the value of the fgr_region_left[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicHeightInLumaSamples−1, inclusive,

the value of the for_region_width[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicWidthInLumaSamples−fgr_region_left[i], inclusive, and

the value of the fgr_region_height[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicHeightInLumaSamples−fgr_region_top[i], inclusive.

3 . The method according to claim 1 ,

wherein the first sample and the second sample are both rectangular.

4 . The method according to claim 1 ,

wherein the first sample and the second sample are at least partly overlapping each other.

5 . A method for video encoding, the method comprising:

obtaining video data comprising at least one picture; and

encoding the video data such that reconstructing the at least one picture comprises reconstructing the at least one picture based on a film grain characteristics SEI message, an alpha channel information SEI message, and at least a first sample and a second sample and at least a third alpha map sample and a fourth alpha map sample, after reconstruction the first sample and the third alpha map sample, and the second sample and the fourth alpha map sample are spatially co-located, and the film grain characteristics SEI message:

specifies coordinates of a top-left corner and a width and a height of a bounding box of an i-th region of a picture by any of an for region_top[i] syntax, an for region left[i] syntax, an for region width[i] syntax, and an for region height[i] syntax, and any of:

a value of the fgr_region_top[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicWidthInLumaSamples−1, inclusive,

a value of the fgr_region left[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicHeightInLumaSamples−1, inclusive,

a value of the fgr_region width[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicWidthInLumaSamples−for region left[i], inclusive, and

a value of the for region height[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicHeightInLumaSamples—fgr_region_top[i], inclusive,

wherein reconstructing the at least one picture further comprises applying film grain synthesis to the first sample based on a first value of the third sample and determining to not apply film grain synthesis to the second sample based on a second value of the fourth sample, wherein the first value and second value are different from each other.

6 . The method according to claim 5 , wherein each of:

the value of the fgr_region_top[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicWidthInLumaSamples−1, inclusive,

the value of the fgr_region_left[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicHeightInLumaSamples−1, inclusive,

the value of the fgr_region_width[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicWidthInLumaSamples−fgr_region_left[i], inclusive, and

the value of the fgr_region_height[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicHeightInLumaSamples−fgr_region_top[i], inclusive.

7 . The method according to claim 5 ,

wherein the first sample and the second sample are both rectangular.

8 . The method according to claim 5 ,

wherein the first sample and the second sample are at least partly overlapping each other.

9 . A method of processing visual media data, the method comprising:

performing a conversion between a visual media file and a bitstream of a visual media data according to a format rule indicating to

obtain video data comprising at least one coded picture;

reconstruct a coded picture comprising a film grain characteristics SEI message, an alpha channel information SEI message, and at least a first sample and a second sample and at least a third alpha map sample and a fourth alpha map sample, wherein after reconstruction the first sample and the third alpha map sample, and the second sample and the fourth alpha map sample are spatially co-located, and the film grain characteristics SEI message:

specifies coordinates of a top-left corner and a width and a height of a bounding box of an i-th region of a picture by any of an for region_top[i] syntax, an for region left[i] syntax, an for region width[i] syntax, and an fgr_region height[i] syntax, and any of:

a value of the for region_top[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicWidthInLumaSamples−1, inclusive,

a value of the for region left[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicHeightInLumaSamples−1, inclusive,

a value of the for region width[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicWidthInLumaSamples−for region left[i], inclusive, and

a value of the for region height[i] syntax is expressed in the film grain characteristics SEI message as in a range of 0 to PicHeightInLumaSamples−fgr_region_top[i], inclusive;

apply film grain synthesis to the first sample based on a first value of the third sample; and

determine to not apply film grain synthesis to the second sample based on a second value of the fourth sample, wherein the first value and second value are different from each other.

10 . The method according to claim 9 , wherein each of:

the value of the fgr_region_top[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicWidthInLumaSamples−1, inclusive,

the value of the fgr_region_left[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicHeightInLumaSamples−1, inclusive,

the value of the fgr_region_width[i] syntax is expressed in the film grain characteristics SEI message as in the range of 0 to PicWidthInLumaSamples−fgr_region_left[i], inclusive, and

the value of the fgr_region_height[i] syntax is expressed in the film grain characteristics SEI message.

11 . The method according to claim 9 ,

wherein the first sample and the second sample are both rectangular.

12 . The method according to claim 2 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:4:4.

13 . The method according to claim 2 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:2:0.

14 . The method according to claim 2 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:2:2.

15 . The method according to claim 6 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:4:4.

16 . The method according to claim 6 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:2:0.

17 . The method according to claim 6 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:2:2.

18 . The method according to claim 6 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:4:4.

19 . The method according to claim 6 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:2:0.

20 . The method according to claim 10 , wherein applying the film grain synthesis to the first sample based on the first value of the third sample comprises simulating film grain in a chroma format 4:2:2.