IP Library Granted Patent US 12,231,632
Granted Patent B2
US 12,231,632 · App. 17/361,973 · Granted Feb 18, 2025

Methods of parameter set selection in cloud gaming system

Inventors: Xiaozhong Xu (State College, PA); Xiang Li (Saratoga, CA); Shan Liu (San Jose, CA)
Assignee: TENCENT AMERICA LLC
H04N19/117G06N20/00H04N19/46H04N19/70H04N19/80
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 12,231,632
App. No.
17/361,973
Granted
Feb 18, 2025
Kind
B2
Abstract

Video coding and decoding methods, apparatuses, and storage medium are provided. The encoding method includes training a model for determining a parameter set to be used for encoding; obtaining a video content; determining the parameter set for encoding the video content using the trained model; encoding the video content according to the parameter set; transmitting the encoded video content to a decoding device; and transmitting the parameter set to the decoding device. The decoding method includes receiving an encoded video content from an encoding device; determining whether a parameter set is received from the encoding device; based on determining that the parameter set is received, decoding the encoded video content according to the parameter set; and transmitting the decoded video content to a display device.

Claims (33)

1. A method of performing video coding in a network-based system, performed by an encoding device, the method comprising:

obtaining a video content;

determining an encoding parameter set for encoding the video content and a decoding parameter set for decoding the video content among multiple parameter sets,

wherein the multiple parameter sets for encoding the video content and decoding the video content are generated using a trained parameter set model,

wherein the encoding parameter set for encoding the video content is selected specifically for an encoding instance and is based on a training data of a content type of the video content,

wherein the decoding parameter set for decoding the video content is selected specifically for a decoding instance and is based on the training data of the content type of the video content, and

wherein the content type of the video content includes a plurality of game types comprising at least one of a game genre and a game title;

encoding the video content according to the encoding parameter set;

transmitting the encoded video content to a decoding device;

transmitting an indicator flag indicating to a decoder that the decoding parameter set is to be used for decoding the video content instead of a default parameter set; and

transmitting the encoding parameter set to the decoding device, wherein the transmitting of the encoding parameter set is distinct from the transmitting of the encoded video content.

2. The method of claim 1 , wherein a parameter set comprises a set of filter coefficients to perform filtering on one or more images of the video content.

3. The method of claim 1 , wherein at least one parameter set is determined for each of the plurality of game types.

4. The method of claim 1 , wherein the default parameter set is transmitted to the decoding device prior to the encoded video content, or wherein more than one default parameter set is transmitted to the decoding device prior to the encoded video content.

5. The method of claim 1 , wherein the determined parameter set is transmitted to the decoding device as metadata.

6. A non-transitory computer-readable storage medium storing computer program code, the computer program code, when executed by at least one processor is configured to perform a method of claim 1 .

7. An encoding device comprising:

at least one memory storing a computer program code; and

at least one processor configured to access the at least one memory and operate as instructed by the computer program code, the computer program code comprising:

obtaining code configured to cause the at least one processor to obtain a video content;

determining code configured to cause the at least one processor to determine an encoding parameter set for encoding the video content and a decoding parameter set for decoding the video content among multiple parameter sets,

wherein the multiple parameter sets for encoding the video content and decoding the video content are generated using a trained parameter set model,

wherein the encoding parameter set for encoding the video content is selected specifically for an encoding instance and is based on a training data of a content type of the video content,

wherein the decoding parameter set for decoding the video content is selected specifically for a decoding instance and is based on the training data of the content type of the video content, and

wherein the content type of the video content includes a plurality of game types comprising at least one of a game genre and a game title;

encoding code configured to cause the at least one processor to encode the video content according to the encoding parameter set;

first transmitting code configured to cause the at least one processor to control a communication interface to transmit the encoded video content to a decoding device;

second transmitting code configured to cause the at least one processor to control the communication interface to transmit an indicator flag indicating to a decoder that the parameter set is to be used for decoding the video content instead of a default parameter set; and

third transmitting code configured to cause the at least one processor to control the communication interface to transmit the encoding parameter set to the decoding device, wherein the transmitting of the encoding parameter set is distinct from the transmitting of the encoded video content.

8. The encoding device of claim 7 , wherein a parameter set comprises a set of filter coefficients to perform filtering on one or more images of the video content.

9. The encoding device of claim 7 , wherein at least one parameter is determined for each of the plurality of game types.

10. The encoding device of claim 7 , wherein the determined parameter set is transmitted to the decoding device as metadata.

11. The encoding device of claim 7 , wherein the default parameter set is transmitted to the decoding device prior to the encoded video content, or wherein more than one default parameter sets is transmitted to the decoding device prior to the encoded video content.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 29, 2021
From: XU, XIAOZHONG; LI, XIANG; LIU, SHAN
To: TENCENT AMERICA LLC
Reel/Frame 056706/0886 →
Continuity (2)
Provisional Application 63062759 · Aug 7, 2020
Related Publication 20220046237A1 · Feb 10, 2022
References Cited (22)
US 20130142251A1 · Maani · 2013 [cited by applicant]
US 20170347112A1 · Zhang · 2017 [cited by examiner]
US 20170359580A1 · Su · 2017 [cited by examiner]
US 20180192046A1 · Teo · 2018 [cited by examiner]
US 20180288419A1 · Yu et al. · 2018 [cited by applicant]
US 20190028705A1 · Xu et al. · 2019 [cited by applicant]
US 20190075301A1 · Chou · 2019 [cited by examiner]
US 20210304355A1 · Delattre · 2021 [cited by examiner]
US 20220070527A1 · Kojima · 2022 [cited by examiner]
CN 111066326A · 2020 [cited by applicant]
JP 2017153145A · 2017 [cited by applicant]
JP 202157766A · 2021 [cited by applicant]
KR 1020160032109A1 · 2016 [cited by applicant]
Shan Liu, “JVET AHG report: Neural Networks in Video Coding (AHG9)”, Joint Video Experts Team (JVET) of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, JVET-J0009-v1, Apr. 10-20, 2018, pp. 1-3, 10th Meeting, San Diego, … [cited by applicant]
Yiming Li, “Methodology and reporting template for neural network coding tool testing”, Joint Video Experts Team (JVET) of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, JVET-M1006-v1, Jan. 9-18, 2019, pp. 1-4, 13th Me… [cited by applicant]
Dong Liu et al., “Deep Learning-Based Technology in Responses to the Joint Call for Proposals on Video Compression with Capability beyond HEVC”, IEEE Transactions on Circuits and Systems for Video Technology, pp. 1-14. [cited by applicant]
Han Zhu et al., “Residual Convolutional Neural Network Based In-Loop Filter With Intra and Inter Frames Processed Respectively for AVS3”, pp. 1-6. [cited by applicant]
International Search Report issued Oct. 5, 2021 in International Application No. PCT/US2021/041250. [cited by applicant]
Written Opinion of the International Searching Authority issued Oct. 5, 2021 in International Application No. PCT/US2021/041250. [cited by applicant]
Extended European Search Report dated Oct. 25, 2022 in European Application No. 21853390.9. [cited by applicant]
Japanese Office Action dated Sep. 5, 2023 in Japanese Application No. 2022-531440. [cited by applicant]
Communication dated Apr. 29, 2023 issued by the Korean Patent Office in application No. 10-2022-7012345. [cited by applicant]