公开(公告)号：US20240282012A1

公开(公告)日：2024-08-22

申请号：US18442622

申请日：2024-02-15

申请人： QUALCOMM Incorporated

发明人： Dmytro Rusanovskyy ,  Samuel James Eadie ,  Yun Li ,  Marta Karczewicz

IPC分类号： G06T9/00 ,  H04N19/105 ,  H04N19/176 ,  H04N19/192 ,  H04N19/70 ,  H04N19/82

CPC分类号： G06T9/002 ,  H04N19/105 ,  H04N19/176 ,  H04N19/192 ,  H04N19/70 ,  H04N19/82

摘要： A video encoder and video decoder are configured to perform a neural network (NN)-based filter process on reconstructed blocks of video data. In one example, the NN-based filter process uses reconstruction samples of the block, prediction samples of the block, and supplementary data related to the block as inputs. The NN-based filter process includes an initial processing of one or more types of the supplementary data with fewer computations relative to the initial processing of the reconstruction samples and the prediction samples.

公开(公告)号：US12028539B2

公开(公告)日：2024-07-02

申请号：US18318953

申请日：2023-05-17

申请人： Adobe Inc.

发明人： Viswanathan Swaminathan ,  Stefano Petrangeli ,  Gwendal Simon

IPC分类号： H04N19/00 ,  H04N19/176 ,  H04N19/186 ,  H04N19/192

CPC分类号： H04N19/192 ,  H04N19/176 ,  H04N19/186

摘要： The present disclosure relates to systems, methods, and non-transitory computer-readable media to enhance texture image delivery and processing at a client device. For example, the disclosed systems can utilize a server-side compression combination that includes, in sequential order, a first compression pass, a decompression pass, and a second compression pass. By applying this compression combination to a texture image at the server-side, the disclosed systems can leverage both GPU-friendly and network-friendly image formats. For example, at a client device, the disclosed system can instruct the client device to execute a combination of decompression-compression passes on a GPU-network-friendly image delivered over a network connection to the client device. In so doing, client device can generate a tri-pass-compressed-texture from a decompressed image comprising texels with color palettes based on previously reduced color palettes from the first compression pass at the server-side, which reduces computational overhead and increases performance speed.

公开(公告)号：US20240205432A1

公开(公告)日：2024-06-20

申请号：US18589756

申请日：2024-02-28

申请人： HUAWEI TECHNOLOGIES CO., LTD.

发明人： Peiyun DI ,  Xin LIU ,  Yi SONG ,  Xiaoyu YANG ,  Xuejian GONG

IPC分类号： H04N19/30 ,  H04N19/105 ,  H04N19/164 ,  H04N19/172 ,  H04N19/192

CPC分类号： H04N19/30 ,  H04N19/105 ,  H04N19/164 ,  H04N19/172 ,  H04N19/192

摘要： The technology of this application relates to an encoding method, an encapsulation method, a display method, an apparatus, and an electronic device. The encoding method includes obtaining a to-be-encoded image, determining N encoding scales (N is an integer greater than 1) for the image, determining an encoding parameter corresponding to each of the N encoding scales, to obtain N groups of encoding parameters, and encoding the image N times by using a preset single-scale encoder based on the N groups of encoding parameters to obtain N groups of bitstream data. In this way, the image is encoded to obtain the bitstream data with a small data amount (namely, the bitstream data with a low encoding scale), so that when a network fluctuates, the bitstream data corresponding to the image can arrive at a decoder side with a higher probability, thereby ensuring smoothness of video playing.

公开(公告)号：US20240187618A1

公开(公告)日：2024-06-06

申请号：US18440013

申请日：2024-02-13

申请人： GOOGLE LLC

发明人： Sam John ,  Balineedu Adsumilli ,  Akshay Gadde

IPC分类号： H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

CPC分类号： H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

摘要： A learning model is trained for rate-distortion behavior prediction against a corpus of a video hosting platform and used to determine optimal bitrate allocations for video data given video content complexity across the corpus of the video hosting platform. Complexity features of the video data are processed using the learning model to determine a rate-distortion cluster prediction for the video data, and transcoding parameters for transcoding the video data are selected based on that prediction. The rate-distortion clusters are modeled during the training of the learning model, such as based on rate-distortion curves of video data of the corpus of the video hosting platform and based on classifications of such video data. This approach minimizes total corpus egress and/or storage while further maintaining uniformity in the delivered quality of videos by the video hosting platform.

公开(公告)号：US11985337B2

公开(公告)日：2024-05-14

申请号：US17586453

申请日：2022-01-27

申请人： Comcast Cable Communications, LLC

发明人： Weidong Mao ,  Alexander Giladi

IPC分类号： H04N19/176 ,  G06V20/40 ,  H04N19/115 ,  H04N19/117 ,  H04N19/154 ,  H04N19/162 ,  H04N19/166 ,  H04N19/17 ,  H04N19/177 ,  H04N19/179 ,  H04N19/192 ,  H04N19/196 ,  H04N19/46 ,  H04N19/517 ,  H04N19/61 ,  H04N21/647

CPC分类号： H04N19/176 ,  G06V20/49 ,  H04N19/166 ,  H04N19/517 ,  H04N21/64738 ,  H04N19/115 ,  H04N19/117 ,  H04N19/154 ,  H04N19/162 ,  H04N19/17 ,  H04N19/177 ,  H04N19/179 ,  H04N19/192 ,  H04N19/196 ,  H04N19/46 ,  H04N19/61

摘要： Systems, apparatuses, and methods are described for encoding a scene of media content based on visual elements of the scene. A scene of media content may comprise one or more visual elements, such as individual objects in the scene. Each visual element may be classified based on, for example, the motion and/or identity of the visual element. Based on the visual element classifications, scene encoder parameters and/or visual element encoder parameters for different visual elements may be determined. The scene may be encoded using the scene encoder parameters and/or the visual element encoder parameters.

公开(公告)号：US20240129554A1

公开(公告)日：2024-04-18

申请号：US18384520

申请日：2023-10-27

申请人： DOLBY INTERNATIONAL AB

发明人： Jie Zhao ,  Christopher A. Segall ,  Louis J. Kerofsky

IPC分类号： H04N19/91 ,  H04N19/119 ,  H04N19/15 ,  H04N19/159 ,  H04N19/17 ,  H04N19/174 ,  H04N19/192 ,  H04N19/43 ,  H04N19/436 ,  H04N19/44 ,  H04N19/46 ,  H04N19/61 ,  H04N19/70

CPC分类号： H04N19/91 ,  H04N19/119 ,  H04N19/15 ,  H04N19/159 ,  H04N19/17 ,  H04N19/174 ,  H04N19/192 ,  H04N19/43 ,  H04N19/436 ,  H04N19/44 ,  H04N19/46 ,  H04N19/61 ,  H04N19/70 ,  H04N19/136

摘要： A method for decoding a video bitstream is disclosed. The method comprises: entropy decoding a first portion of a video bitstream, wherein first portion of video bitstream is associated with a video frame, thereby producing a first portion of decoded data; entropy decoding a second portion of video bitstream, wherein second portion of video bitstream is associated with video frame, thereby producing a second portion of decoded data, wherein entropy decoding second portion of video bitstream is independent of entropy decoding first portion of video bitstream; and reconstructing a first portion of video frame associated with video bitstream using first portion of decoded data and second portion of decoded data.

公开(公告)号：US20240080445A1

公开(公告)日：2024-03-07

申请号：US18507582

申请日：2023-11-13

申请人： Comcast Cable Communications, LLC

发明人： Kyong Park ,  James W. Fahrny

IPC分类号： H04N19/127 ,  H04L65/75 ,  H04N19/154 ,  H04N19/187 ,  H04N19/192 ,  H04N21/2343 ,  H04N21/254 ,  H04N21/4627 ,  G06F21/10

CPC分类号： H04N19/127 ,  H04L65/762 ,  H04N19/154 ,  H04N19/187 ,  H04N19/192 ,  H04N21/23439 ,  H04N21/2541 ,  H04N21/4627 ,  G06F21/101 ,  G06Q2220/16

摘要： Methods and systems related to authoring and acquiring digital rights management (DRM) licenses are disclosed. For example, a computing device may generate or author a digital rights management license for a content asset that includes one or more usage restriction rules. A usage restriction may limit the maximum display resolution for a content asset. Another device may then receive the license and process the one or more usage restrictions prior to presentation of the content asset to a user.

公开(公告)号：US11924449B2

公开(公告)日：2024-03-05

申请号：US17908352

申请日：2020-05-19

申请人： Google LLC

发明人： Sam John ,  Balineedu Adsumilli ,  Akshay Gadde

IPC分类号： H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

CPC分类号： H04N19/40 ,  H04N19/119 ,  H04N19/147 ,  H04N19/184 ,  H04N19/192

摘要： A learning model is trained for rate-distortion behavior prediction against a corpus of a video hosting platform and used to determine optimal bitrate allocations for video data given video content complexity across the corpus of the video hosting platform. Complexity features of the video data are processed using the learning model to determine a rate-distortion cluster prediction for the video data, and transcoding parameters for transcoding the video data are selected based on that prediction. The rate-distortion clusters are modeled during the training of the learning model, such as based on rate-distortion curves of video data of the corpus of the video hosting platform and based on classifications of such video data. This approach minimizes total corpus egress and/or storage while further maintaining uniformity in the delivered quality of videos by the video hosting platform.

公开(公告)号：US11909971B2

公开(公告)日：2024-02-20

申请号：US18468561

申请日：2023-09-15

申请人： Industry Academy Cooperation Foundation of Sejong University

发明人： Joo Hee Moon ,  Sung Won Lim ,  Dong Jae Won

IPC分类号： H04N19/119 ,  H04N19/105 ,  H04N19/176 ,  H04N19/192 ,  H04N19/96

CPC分类号： H04N19/119 ,  H04N19/105 ,  H04N19/176 ,  H04N19/192 ,  H04N19/96

摘要： The present invention provides an image encoding method and an image decoding method. The image encoding method of the present invention comprises: a first dividing step of dividing a current image into a plurality of blocks; and a second dividing step of dividing, into a plurality of sub blocks, a block, which is to be divided and includes a boundary of the current image, among the plurality of blocks, wherein the second dividing step is recursively performed by setting a sub block including the boundary of the current images as the block to be divided, until the sub block including the boundary of the current image does not exist among the sub blocks.

公开(公告)号：US20230300347A1

公开(公告)日：2023-09-21

申请号：US18202772

申请日：2023-05-26

申请人： HYUNDAI MOTOR COMPANY ,  KIA CORPORATION ,  EWHA UNIVERSITY - INDUSTRY COLLABORATION FOUNDATION

发明人： Je Won Kang ,  Seung Wook Park

IPC分类号： H04N19/176 ,  H04N19/44 ,  H04N19/136 ,  H04N19/192

CPC分类号： H04N19/176 ,  H04N19/44 ,  H04N19/136 ,  H04N19/192

摘要： A video codec uses a block-based deep learning model. The video codec, when processing video blocks by using a deep learning model, generates a super block by stacking or packing the respective ones of YUV video blocks and inputs the generated super block to the deep learning model. The video codec processes the inputs differently in the course of performing convolution within the deep learning model, according to the characteristics of the constituent YUV blocks of the super block