EP-4736443-A1 - ENHANCED OBJECT MASK SEI MESSAGE

Abstract

Systems, methods, and instrumentalities are disclosed herein associated with enhanced object mask SEI messages. In examples, a video device may obtain one or more syntax elements associated with video data. The one or more syntax elements may specify parameters (e.g., location parameters) associated with an object mask associated with a picture. The parameters may be related at least to a sample range of object mask samples around an object mask ID value. In examples, the parameters associated with the object mask may include a maximum sample value of the object mask and a minimum sample value defining the range of the object mask samples around the object mask ID value. In examples, the parameters associated with the object mask may be bounding box parameters associated with the object mask.

Inventors

• FRANCOIS, EDOUARD
• DOYEN, DIDIER
• DE LAGRANGE, Philippe
• SALMON-LEGAGNEUR, CHARLES

Assignees

• InterDigital CE Patent Holdings, SAS

Dates

Publication Date

20260506

Application Date

20240611

Claims (17)

1. 1. A video decoding device, the device comprising : a processor configured to: obtain, in video data, an object mask parameter indication associated with an object mask in an auxiliary picture associated with a primary picture; determine a plurality of parameters associated with the object mask based on the object mask parameter indication; and derive the object mask based on the plurality of parameters.
2. 2. A video decoding method, the method comprising: obtaining, in video data, an object mask parameter indication associated with an object mask in an auxiliary picture associated with a primary picture; determining a plurality of parameters associated with the object mask based on the object mask parameter indication; and deriving the object mask based on the plurality of parameters.
3. 3. The video decoding device of claim 1 or the video decoding method of claim 2, wherein the object mask parameter indication is an object mask bounding box indication, and wherein the processor of claim 1 is further configured to perform, or the method of claim 2 further comprises: determining a plurality of object mask bounding box parameters associated with the object mask based on the object mask bounding box indication, wherein the object mask is derived based on the plurality of object mask bounding box parameters.
4. 4. The video decoding device of any one of claims 1 and 3 or the video decoding method of any one of claims 2 to 3, wherein the auxiliary picture is a sub-window within the primary picture, and wherein the plurality of bounding box parameters associated with the object mask comprise a top left x location, a top left y location, an object mask width, and an object mask height within the auxiliary picture.
5. 5. The video decoding device of claim 1 or the video decoding method of claim 2, wherein the object mask parameter indication is an object mask location indication, and wherein the processor of claim 1 is further configured to perform, or the method of claim 2 further comprises: determining a plurality of object mask location parameters based on the object mask location indication, wherein the object mask is derived based on the plurality of object mask location parameters.
6. 6. The video decoding device of any one of claims 1 and 5 or the video decoding method of any one of claims 2 and 5, wherein the plurality of object mask location parameters comprises a maximum sample value and a minimum sample value defining a range of object mask samples.
7. 7. The video decoding device of any one of claims 1 and 5 or the video decoding method of any one of claims 2 and 5, wherein the plurality of object mask location parameters comprises a sample tolerance value of object mask samples.
8. 8. A video encoding device, the device comprising: a processor configured to: identify an object mask in an auxiliary picture associated with a primary picture; determine a plurality of parameters associated with the object mask; and signal, in video data, an object mask parameter indication based on the plurality of parameters associated with the object mask.
9. 9. A video encoding method, the method comprising: identifying an object mask in an auxiliary picture associated with a primary picture; determining a plurality of parameters associated with the object mask; and signaling, in video data, an object mask parameter indication based on the plurality of parameters associated with the object mask.
10. 10. The video encoding device of claim 8 or the video encoding method of claim 9, wherein the plurality of parameters associated with the object mask is a plurality of object mask bounding box parameters, and wherein the processor of claim 8 is further configured to perform, or the method of claim 9 further comprises: signaling an object mask bounding box indication based on the plurality of object mask bounding box parameters.
11. 11 . The video encoding device of any one of claims 8 and 10 or the video encoding method of any one of claims 9 to 10, wherein the auxiliary picture is a sub-window within the primary picture, and wherein the plurality of bounding box parameters associated with the object mask comprise a top left x location, a top left y location, an object mask width, and an object mask height within the auxiliary picture.
12. 12. The video encoding device of claim 8 or the video encoding method of claim 9, wherein the plurality of parameters associated with the object mask is a plurality of object mask location parameters, and wherein the processor of claim 8 is further configured to perform, or the method of claim 9 further comprises: signaling an object mask location indication based on the plurality of object mask location parameters.
13. 13. The video encoding device of any one of claims 8 and 12 or the video encoding method of any one of claims 9 and 12, wherein the plurality of object mask location parameters comprises a maximum sample value and a minimum sample value defining a range of object mask samples.
14. 14. The video encoding device of any one of claims 8 and 12 or the video encoding method of any one of claims 9 and 12, wherein the plurality of object mask location parameters comprises a sample tolerance value of object mask samples.
15. 15. A computer program product which is stored on a non-transitory computer readable medium and comprises program code instructions for implementing the steps of a method according to at least one of claims 2 to 7 and 9 to 14 when executed by a processor.
16. 16. A computer program comprising program code instructions for implementing the steps of a method according to at least one of claims 2 to 7 and 9 to 14 when executed by a processor.
17. 17. A video data comprising information representative of the encoded output generated according to one of the methods of any of claims 9 to 14.

Description

ENHANCED OBJECT MASK SEI MESSAGE CROSS-REFERENCE TO RELATED APPLICATIONS [0001] This application claims the benefit of European Patent Application 23306137.3, filed July 5, 2023, and European Patent Application 233061 15.9, filed June 30, 2023, the disclosures of which are incorporated herein by reference in their entireties. BACKGROUND [0002] Video coding systems may be used to compress digital video signals, e.g., to reduce the storage and/or transmission bandwidth needed for such signals. Video coding systems may include, for example, block-based, wavelet-based, and/or object-based systems. SUMMARY [0003] Systems, methods, and instrumentalities are disclosed herein associated with enhanced object mask SEI messages. [0004] In examples, a video encoding device may identify an object mask in an auxiliary picture associated with a primary picture. The video encoding device may determine a plurality of parameters associated with the object mask. An object mask parameter indication may be signaled in video data based on the plurality of parameters associated with the object mask. [0005] In examples, the plurality of parameters associated with the object mask may be a plurality of object mask bounding box parameters. Based on determining the plurality of object mask bounding box parameters, an object mask bounding box indication may be signaled. In examples, the auxiliary picture may be a sub-window within the primary picture. The plurality of bounding box parameters associated with the object mask may include a top left x location, a top left y location, an object mask width, and an object mask height within the auxiliary picture. [0006] In examples, the plurality of parameters associated with the object mask may be a plurality of object mask location parameters. Based on determining the plurality of object mask location parameters, an object mask location indication may be signaled. In examples, the plurality of object mask location parameters may include a maximum sample value and a minimum sample value defining a range of object mask samples. In examples, the plurality of object mask location parameters may include a sample tolerance value of object mask samples. [0007] In examples, a video decoding device may obtain, in video data, an object mask parameter indication associated with an object mask in an auxiliary picture associated with a primary picture. The video decoder may determine a plurality of parameters associated with the object mask based on the object mask parameter indication. The object mask may be derived based on the plurality of parameters. [0008] In examples, the object mask parameter indication may be an object mask bounding box indication. Based on the object mask bounding box indication, a plurality of object mask bounding box parameters associated with the object mask may be determined. The object mask may be derived based on the plurality of object mask bounding box parameters. In examples, the auxiliary picture may be a sub-window within the primary picture. The plurality of bounding box parameters associated with the object mask may include a top left x location, a top left y location, an object mask width, and an object mask height within the auxiliary picture. [0009] In examples, the object mask parameter indication may be an object mask location indication. Based on the object mask location indication, a plurality of object mask location parameters associated with the object mask may be determined. The object mask may be derived based on the plurality of object mask location parameters. In examples, the plurality of object mask location parameters may include a maximum sample value and a minimum sample value defining a range of object mask samples. In examples, the plurality of object mask location parameters may include a sample tolerance value of object mask samples. [0010] In examples, a video device may obtain one or more syntax elements associated with video data. The one or more syntax elements may specify parameters (e.g., location parameters) associated with an object mask associated with a picture. The parameters may be related at least to a sample range of object mask samples around an object mask ID value. In examples, the parameters associated with the object mask may include a maximum sample value of the object mask and a minimum sample value defining the range of the object mask samples around the object mask ID value. In examples, the parameters associated with the object mask may be bounding box parameters associated with the object mask. [0011] Systems, methods, and instrumentalities described herein may involve a decoder. In some examples, the systems, methods, and instrumentalities described herein may involve an encoder. In some examples, the systems, methods, and instrumentalities described herein may involve a signal (e.g., from an encoder and/or received by a decoder). A computer-readable medium may include instructions for causing one or more processors