公开(公告)号：US20240323414A1

公开(公告)日：2024-09-26

申请号：US18731860

申请日：2024-06-03

申请人： DOLBY LABORATORIES LICENSING CORPORATION

发明人： Neil W. Messmer ,  Robin Atkins ,  Steve Margerm ,  Peter W. Longhurst

IPC分类号： H04N19/30 ,  G06F3/14 ,  G06T9/00 ,  G09G5/02 ,  H04N1/60 ,  H04N9/69 ,  H04N21/235 ,  H04N21/4402

CPC分类号： H04N19/30 ,  G06T9/00 ,  G09G5/02 ,  H04N1/603 ,  H04N9/69 ,  H04N21/235 ,  H04N21/440227 ,  G06F3/1454

摘要： Several embodiments of scalable image processing systems and methods are disclosed herein whereby color management processing of source image data to be displayed on a target display is changed according to varying levels of metadata.

公开(公告)号：US12101478B2

公开(公告)日：2024-09-24

申请号：US18386314

申请日：2023-11-02

申请人： Texas Instruments Incorporated

发明人： Madhukar Budagavi

IPC分类号： H04N19/117 ,  G06T9/00 ,  H04N19/167 ,  H04N19/172 ,  H04N19/176 ,  H04N19/182 ,  H04N19/192 ,  H04N19/61 ,  H04N19/82 ,  H04N19/86

CPC分类号： H04N19/117 ,  G06T9/00 ,  H04N19/167 ,  H04N19/172 ,  H04N19/176 ,  H04N19/182 ,  H04N19/192 ,  H04N19/61 ,  H04N19/82 ,  H04N19/86

摘要： Virtual boundary processing in adaptive loop filtering (ALF) requires that padded values be substituted for unavailable pixel rows outside the virtual boundaries. Methods and apparatus are provided for virtual boundary processing in ALF that allow the use of more actual pixel values for padding than in the prior art.

公开(公告)号：US20240314340A1

公开(公告)日：2024-09-19

申请号：US18669168

申请日：2024-05-20

申请人： LG ELECTRONICS INC.

发明人： Hendry HENDRY

IPC分类号： H04N19/31 ,  G06T9/00 ,  H04N19/169 ,  H04N19/172

CPC分类号： H04N19/31 ,  G06T9/00 ,  H04N19/172 ,  H04N19/188

摘要： According to embodiment(s) of the present document, multilayer-based coding can be performed. The multilayer-based coding can include a sub-bitstream extraction process. Inputs of the sub-bitstream extraction process can include a value related toa target OLS index and a value related to a highest temporal identifier.

公开(公告)号：US20240312064A1

公开(公告)日：2024-09-19

申请号：US18575548

申请日：2021-07-02

申请人： Beijing Xiaomi Mobile Software Co., Ltd. ,  Xidian University

发明人： Wei ZHANG ,  Mary-Luc Georges Henry CHAMPEL ,  Shuo GAO

IPC分类号： G06T9/00

CPC分类号： G06T9/001

摘要： A method for encoding, in a bitstream, point attributes associated to a point of a point cloud, includes: determining, for a point P to be encoded to the bitstream, a predictor list of k predictor points of the point cloud including k points of the point cloud nearest to the point P to be encoded, wherein the k points are selected according to their relative position to each other; and encoding the point attributes associated to the point P to be encoded by predictive encoding based on attributes of the predictor points of the predictor list.

公开(公告)号：US20240303870A1

公开(公告)日：2024-09-12

申请号：US18179487

申请日：2023-03-07

申请人： ADOBE INC.

发明人： Defu Cao ,  Zhaowen Wang ,  Jose Ignacio Echevarria Vallespi

IPC分类号： G06T9/00 ,  G06T7/155 ,  G06T7/60 ,  G06T11/00

CPC分类号： G06T9/002 ,  G06T7/155 ,  G06T7/60 ,  G06T11/00 ,  G06T2207/20044 ,  G06T2207/20072 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Systems and methods for generating representations for vector graphics are described. Embodiments are configured to obtain semantic information and geometric information for a vector graphics image. The semantic information describes individual segments of the vector graphics image, and the geometric information describes geometric relationships among the individual segments. Embodiments are additionally configured to encode the semantic information and the geometric information to obtain a vector graphics representation for the vector graphics image, and to provide a reconstructed image based on the vector graphics representation.

公开(公告)号：US12087025B2

公开(公告)日：2024-09-10

申请号：US17916245

申请日：2021-11-16

申请人： i-Scream arts Co., Ltd.

发明人： Ji-hoon Kim ,  Ki-seok Park

IPC分类号： G06T9/00 ,  A61B5/00 ,  A61B5/16 ,  G06T11/20

CPC分类号： G06T9/002 ,  A61B5/165 ,  G06T11/203 ,  A61B5/7264 ,  G06T2200/24 ,  G06T2210/22

摘要： A device for generating data for art-based psychoanalysis according to one embodiment of the present disclosure may include: a user interface which provides a user, i.e., an examinee with an interactive environment; a first drawing analysis part which is subjected to learning using a first artificial intelligence model, analyzes drawing data which the user input through the user interface to crop regional data of interest from the drawing data, and compresses the data of a region of interest or uncompresses the compressed data of a region of interest to restore the drawing data; a storing part which stores labeling information of the size, location and angle of an object included in the compressed data of a region of interest; and a second drawing analysis equipped with a second artificial intelligence model that partially augments an object of an art-based psychoanalytic element included in the drawing data, followed by learning.

公开(公告)号：US12087024B2

公开(公告)日：2024-09-10

申请号：US16811219

申请日：2020-03-06

申请人： Disney Enterprises, Inc. ,  ETH ZÜRICH

发明人： Abdelaziz Djelouah ,  Leonhard Markus Helminger ,  Scott Labrozzi ,  Yuanyi Xue ,  Erika Varis Doggett ,  Jared McPhillen ,  Christopher Richard Schroers

IPC分类号： H04N19/60 ,  G06T9/00 ,  H04N19/126 ,  H04N19/91

CPC分类号： G06T9/002 ,  H04N19/126 ,  H04N19/60 ,  H04N19/91

摘要： According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image, and quantize the latent space representation of the input image to produce multiple quantized latents. The hardware processor further executes the software code to encode the quantized latents using a probability density function of the latent space representation of the input image, to generate a bitstream, and convert the bitstream into an output image corresponding to the input image. The probability density function of the latent space representation of the input image is obtained based on a normalizing flow mapping of one of the input image or the latent space representation of the input image.

公开(公告)号：US12087022B2

公开(公告)日：2024-09-10

申请号：US17058621

申请日：2019-05-29

申请人： Magic Leap, Inc.

发明人： Henry Engelland-Gay ,  Clay Heins

IPC分类号： G06K9/00 ,  G06T3/40 ,  G06T7/73 ,  G06T9/00 ,  G06T17/20

CPC分类号： G06T9/001 ,  G06T3/40 ,  G06T7/75 ,  G06T17/205

摘要： Systems and methods for compressing dynamic unstructured point clouds. A dynamic unstructured point cloud can be mapped to a skeletal system of a subject to form one or more structured point cloud representations. One or more sequences of the structured point cloud representations can be formed. The one or more sequences of structured point cloud representations can then be compressed.

公开(公告)号：US12087020B2

公开(公告)日：2024-09-10

申请号：US17475853

申请日：2021-09-15

申请人： Synaptics Incorporated

发明人： Matteo Naccari ,  Scott Liam Ransom

IPC分类号： G06T9/00 ,  H04N19/126 ,  H04N19/146 ,  H04N19/172 ,  H04N19/184

CPC分类号： G06T9/00 ,  H04N19/126 ,  H04N19/146 ,  H04N19/172 ,  H04N19/184

摘要： Systems and methods for controlling compression of image data by a quality controller include obtaining a desired target number of bits to be generated from compression of a current image area using a predetermined compression protocol, determining a calculated quantisation level based on the desired number of bits using a predetermined relationship between the number of bits and quantisation level, selecting a discrete quantisation level from a plurality of predetermined discrete quantisation levels based on the calculated quantisation level, determining a predicted number of bits that would result from compression of the current image area at the selected discrete quantisation level using the predetermined relationship, determining whether the predicted number of bits exceeds the desired number of bits and, if not, providing to an encoder information to enable the encoder to determine a set of compression parameters associated with the selected discrete quantisation level.

公开(公告)号：US20240296935A1

公开(公告)日：2024-09-05

申请号：US18438640

申请日：2024-02-12

申请人： Siemens Healthineers AG

发明人： Yue Zhang ,  Marc Demoustier ,  Venkatesh Narasimha Murthy ,  Florin-Cristian Ghesu ,  Dorin Comaniciu

IPC分类号： G16H30/40 ,  G06T7/12 ,  G06T7/20 ,  G06T9/00 ,  G06V10/80

CPC分类号： G16H30/40 ,  G06T7/12 ,  G06T7/20 ,  G06T9/00 ,  G06V10/806 ,  G06V2201/03 ,  G06V2201/07

摘要： A position prediction of a target is provided based on a segmentation of a context of the target. Alternatively, or additionally, to a spatial context of the target, it is also possible to consider a temporal context. A catheter tip can be tracked.