公开(公告)号：US20230098577A1

公开(公告)日：2023-03-30

申请号：US17945024

申请日：2022-09-14

申请人： Tencent America LLC

发明人： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC分类号： H04N21/43 ,  G06T7/60 ,  G06T7/50 ,  G06T7/70 ,  G06T7/40 ,  H04S7/00

摘要： Media content data of an object is received. Whether a first parameter indicated by a first description of the object in an acoustic scene and a second parameter indicated by a second description of the object in a visual scene are inconsistent is determined. Based on the first parameter indicated by the first description of the object in the acoustic scene and the second parameter indicated by the second description of the object in the visual scene being inconsistent, one of the first description of the object in the acoustic scene and the second description of the object in the visual scene is modified based on another one of the first description and the second description that is not modified, wherein the modified one of the first description and the second description is consistent with the other one of the first description and the second description that is not modified.

公开(公告)号：US20230007425A1

公开(公告)日：2023-01-05

申请号：US17751425

申请日：2022-05-23

申请人： Tencent America LLC

发明人： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC分类号： H04S7/00 ,  G10L19/16

摘要： Aspects of the disclosure provide methods and apparatuses for audio processing. In some examples, an apparatus for media processing includes processing circuitry. The processing circuitry receive audio inputs associated with a layered description for a space of interest in an audio scene. The space of interest includes a plurality of subspaces. The layered description includes a first layer and a second layer. The first layer has a common node with a first value that is a common attribute value of two or more subspaces in the plurality of subspaces. The second layer has individual nodes respectively associated with each of the plurality of subspaces. The processing circuitry determines the plurality of subspaces of the space of interest based on the layered description, and renders an audio output based on the audio inputs in response to a location of a subject of the audio scene being in the space of interest.

公开(公告)号：US20230007349A1

公开(公告)日：2023-01-05

申请号：US17752551

申请日：2022-05-24

申请人： Tencent America LLC

发明人： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC分类号： H04N21/475

摘要： Aspects of the disclosure provide methods and apparatuses for subjective evaluation. In some examples, processing circuitry receives scores graded by a subject to a media presentation. The scores by the subject includes a plurality of self comparison scores that are graded to self comparison tests in the media presentation. The processing circuitry applies a first rule and a second rule to the plurality of self comparison scores. The first rule requires a first subset of the plurality of self comparison scores in a first range. The second rule requires a second subset of the plurality of self comparison scores in a second range to limit at least an outlier to the first rule according to the second range. The processing circuitry determines that the scores by the subject are qualified for the subjective evaluation in response to the first rule and the second rule being satisfied.

公开(公告)号：US20220391167A1

公开(公告)日：2022-12-08

申请号：US17828755

申请日：2022-05-31

申请人： Tencent America LLC

发明人： Shan LIU ,  Jun TIAN ,  Xiaozhong XU

IPC分类号： G06F3/16 ,  H04R3/04 ,  G10L15/22

摘要： Aspects of the disclosure provide methods and apparatuses (e.g., client devices and server devices) for audio processing. In some examples, a client device includes processing circuitry. The processing circuitry transmits, to a server device, a selection signal indicative of an audio encoding configuration for encoding audio content in an audio input. The processing circuitry receives, from the server device, an encoded bitstream in response to the transmitting of the selection signal. The encoded bitstream includes the audio content that is encoded according to the audio encoding configuration. The processing circuitry renders audio signals based on the encoded bitstream.

公开(公告)号：US20220345752A1

公开(公告)日：2022-10-27

申请号：US17703292

申请日：2022-03-24

申请人： TENCENT AMERICA LLC

发明人： Wei JIANG ,  Wei WANG ,  Sheng LIN ,  Xiaozhong XU ,  Shan LIU

IPC分类号： H04N19/82 ,  H04N19/117 ,  H04N19/86

摘要： A method and apparatus of for video enhancement based on neural network based loop filtering using meta learning may include receiving reconstructed video data; receiving one or more quality factors associated with the reconstructed video data; determining a neural network based loop filter comprising neural network based loop filter parameters and a plurality of layers, wherein the neural network based loop filter parameters include shared parameters and adaptive parameters; and generating enhanced video data with artefact reduction, based on the one or more quality factors and the reconstructed video data, using a neural network based loop filter, wherein the neural network based loop filter comprises neural network based loop filter parameters that include shared parameters and adaptive parameters.

公开(公告)号：US20220270626A1

公开(公告)日：2022-08-25

申请号：US17450015

申请日：2021-10-05

申请人： TENCENT AMERICA LLC

发明人： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC分类号： G10L21/003 ,  G10L21/04

摘要： Aspects of the disclosure provide methods and apparatuses for audio processing. In some examples, an apparatus of audio coding includes processing circuitry. The processing circuitry decodes, from a coded bitstream, information indicative of an adjusted speech signal and a loudness adjustment to the adjusted speech signal. The adjusted speech signal is indicated in an association with multiple speech signals in a scene of an immersive media application. The processing circuitry determines a plurality of loudness adjustments to sound signals including the multiple speech signals in the scene based the plurality of loudness adjustment to the adjusted speech signal, and generates the sound signals in the scene based on the loudness adjustments to the sound signals.

公开(公告)号：US20220239935A1

公开(公告)日：2022-07-28

申请号：US17486533

申请日：2021-09-27

申请人： TENCENT AMERICA LLC

发明人： Wei JIANG ,  Wei WANG ,  Ding DING ,  Shan LIU ,  Xiaozhong XU

IPC分类号： H04N19/44 ,  H04N19/119 ,  H04N19/159 ,  H04N19/70 ,  H04N19/176 ,  G06N3/02

摘要： A method of video decoding at a video decoder can include receiving one or more syntax elements associated with a current first block that belongs to a plurality of first blocks partitioned from a picture, the one or more syntax elements indicating an optimal partition indicating how the current first block is partitioned into second blocks for intra-prediction, a set of block selection signals, wherein the current first block is re-partitioned into third blocks, each block selection signal corresponds to one of the third blocks and indicates whether the respective third block is coded using a first coding method or a second coding method, and a set of compressed representations each corresponding to one of the third blocks. The current first block can be reconstructed based on the one or more syntax elements to generate a reconstructed current first block.

公开(公告)号：US20220217403A1

公开(公告)日：2022-07-07

申请号：US17476824

申请日：2021-09-16

申请人： TENCENT AMERICA LLC

发明人： Byeongdoo CHOI ,  Zeqiang LI ,  Wei JIANG ,  Wei WANG ,  Xiaozhong XU ,  Stephan WENGER ,  Shan LIU

IPC分类号： H04N19/70 ,  H04N19/184 ,  H04N19/42 ,  G06N3/04

摘要： There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining a video bitstream, coding the video bitstream at least partly by a neural network, determining topology information and parameters of the neural network, signaling the determined topology information and the parameters of the neural network in a plurality of syntax elements associated with the coded video bitstream.

公开(公告)号：US20220215592A1

公开(公告)日：2022-07-07

申请号：US17462287

申请日：2021-08-31

申请人： TENCENT AMERICA LLC

发明人： Wei JIANG ,  Wei WANG ,  Ding DING ,  Shan LIU ,  Xiaozhong XU

IPC分类号： G06T9/00 ,  H04N19/124 ,  H04N19/13 ,  H04N19/159 ,  H04N19/176 ,  G06N3/04

摘要： A method of decoding an image with latent feature-domain intra-prediction is performed by at least one processor and includes receiving a set of latent blocks and for each of the blocks in the set of latent blocks: predicting a block, based on a set of previously recovered blocks; receiving a selection signal indicating a currently recovered block, based on the selection signal performing one of (1) and (2): (1) generating a compact residual, a set of residual context parameters, a decoded residual, and generating a first decoded block; (2) generating a second decoded block, based on a compact representation block and a set of context parameters. The method further includes generating a set of recovered blocks comprising each of the currently recovered blocks; generating a recovered latent image by merging all the blocks in the set of recovered blocks; and decoding the recovered latent image, to obtain a reconstructed image.

公开(公告)号：US20220150530A1

公开(公告)日：2022-05-12

申请号：US17526054

申请日：2021-11-15

申请人： TENCENT AMERICA LLC

发明人： Guichun LI ,  Xiang LI ,  Xiaozhong XU ,  Shan LIU

IPC分类号： H04N19/513 ,  H04N19/98 ,  H04N19/159 ,  H04N19/70

摘要： A method, computer program, and computer system for video coding is provided. Video data including at least two frames is received. A motion vector difference is calculated between two frames from among the at least two frames. An adaptive motion vector resolution usage flag is checked. The adaptive motion vector resolution flag may correspond to a precision value and an adaptive motion vector resolution usage value corresponding to whether adaptive motion vector resolution is enabled or disabled. The video data is encoded based on the adaptive motion vector resolution usage value, whereby the motion vector difference is encoded based on the precision value.